Pub Date : 1996-08-06DOI: 10.1109/HPDC.1996.546209
H. Soliman, Adel Said Elmaghraby
An efficient adaptive approach for parallel and distributed simulation (PADS) is formalized and implemented. The aggressive adaptive-risk (AAR) approach aims at reducing cascading rollbacks in large and complex simulations by clustering optimistic logical processes on each processor, and providing these processes the ability to adjust their degree of risk, at run time, to a good operating point based on observed behavior. The AAR approach is used to develop the Clustered Adaptive Distributed Simulator (CADS), which is implemented on a network of workstations. Details of the CADS implementation are described. Performance results for large synthetic loads are reported and compared to those obtained for the Time Warp optimistic technique.
{"title":"An efficient clustered adaptive-risk technique for distributed simulation","authors":"H. Soliman, Adel Said Elmaghraby","doi":"10.1109/HPDC.1996.546209","DOIUrl":"https://doi.org/10.1109/HPDC.1996.546209","url":null,"abstract":"An efficient adaptive approach for parallel and distributed simulation (PADS) is formalized and implemented. The aggressive adaptive-risk (AAR) approach aims at reducing cascading rollbacks in large and complex simulations by clustering optimistic logical processes on each processor, and providing these processes the ability to adjust their degree of risk, at run time, to a good operating point based on observed behavior. The AAR approach is used to develop the Clustered Adaptive Distributed Simulator (CADS), which is implemented on a network of workstations. Details of the CADS implementation are described. Performance results for large synthetic loads are reported and compared to those obtained for the Time Warp optimistic technique.","PeriodicalId":267002,"journal":{"name":"Proceedings of 5th IEEE International Symposium on High Performance Distributed Computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1996-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113993215","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 : 1996-08-06DOI: 10.1109/HPDC.1996.546179
Ian T Foster, S. Tuecke
We use the term ubiquitous supercomputing to refer to systems that integrate low and mid range computing systems, advanced networks, and remote high end computers with the goal of enhancing the computational power accessible from local environments. Such systems promise to enable new applications in areas as diverse as smart instruments and collaborative environments. However, they also demand tools for transporting code between computers and for establishing flexible, dynamic communication structures. We propose that these requirements be satisfied by enhancing the Java programming language with global pointer and remote service request mechanisms from a communication library called Nexus. Java supports transportable code; Nexus provides communication support. We explain how this NexusJava library is implemented and illustrate its use with examples.
{"title":"Enabling technologies for Web-based ubiquitous supercomputing","authors":"Ian T Foster, S. Tuecke","doi":"10.1109/HPDC.1996.546179","DOIUrl":"https://doi.org/10.1109/HPDC.1996.546179","url":null,"abstract":"We use the term ubiquitous supercomputing to refer to systems that integrate low and mid range computing systems, advanced networks, and remote high end computers with the goal of enhancing the computational power accessible from local environments. Such systems promise to enable new applications in areas as diverse as smart instruments and collaborative environments. However, they also demand tools for transporting code between computers and for establishing flexible, dynamic communication structures. We propose that these requirements be satisfied by enhancing the Java programming language with global pointer and remote service request mechanisms from a communication library called Nexus. Java supports transportable code; Nexus provides communication support. We explain how this NexusJava library is implemented and illustrate its use with examples.","PeriodicalId":267002,"journal":{"name":"Proceedings of 5th IEEE International Symposium on High Performance Distributed Computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1996-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134062220","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 : 1996-08-06DOI: 10.1109/HPDC.1996.546210
S. Figueira, F. Berman
Fast networks have made it possible to coordinate distributed heterogeneous CPU, memory and storage resources to provide a powerful platform for executing high-performance applications. However, the performance of these applications on such systems is highly dependent on the allocation and efficient coordination of application tasks. A key component for a performance-efficient allocation strategy is a predictive model which provides a realistic estimate of application performance under varying resource loads. In this paper, we present a model for predicting the effects of contention on application behavior in heterogeneous systems. In particular, our model calculates the slowdown imposed on communication and computation for non-dedicated two-machine heterogeneous platforms. We describe the model for the Sun/CM2 and Sun/Paragon coupled heterogeneous systems. We present experiments on production systems with emulated contention which show the predicted communication and computation costs to be within 15% on average of the actual costs.
{"title":"Modeling the effects of contention on the performance of heterogeneous applications","authors":"S. Figueira, F. Berman","doi":"10.1109/HPDC.1996.546210","DOIUrl":"https://doi.org/10.1109/HPDC.1996.546210","url":null,"abstract":"Fast networks have made it possible to coordinate distributed heterogeneous CPU, memory and storage resources to provide a powerful platform for executing high-performance applications. However, the performance of these applications on such systems is highly dependent on the allocation and efficient coordination of application tasks. A key component for a performance-efficient allocation strategy is a predictive model which provides a realistic estimate of application performance under varying resource loads. In this paper, we present a model for predicting the effects of contention on application behavior in heterogeneous systems. In particular, our model calculates the slowdown imposed on communication and computation for non-dedicated two-machine heterogeneous platforms. We describe the model for the Sun/CM2 and Sun/Paragon coupled heterogeneous systems. We present experiments on production systems with emulated contention which show the predicted communication and computation costs to be within 15% on average of the actual costs.","PeriodicalId":267002,"journal":{"name":"Proceedings of 5th IEEE International Symposium on High Performance Distributed Computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1996-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130431912","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 : 1996-08-06DOI: 10.1109/HPDC.1996.546206
Xue Li, M. Ammar
Real-time multicast video distribution is an important component of many multimedia applications. Our work addresses the fairness problem in feedback-controlled multicast video distribution systems over best effort networks (such as the Internet). We have proposed, implemented and experimented with a scheme called destination set grouping (DSG), where a source maintains a small number of video streams, all carrying the same video but each targeted at receivers with different capabilities. Each stream is feedback-controlled within prescribed limits by its group of receivers. Receivers may move among groups as their capabilities or the capabilities of the network paths leading to them change. In this paper, we focus on the potential for network overloading caused by the transmission of multiple replicated streams. We propose a number of mechanisms to be implemented at the source and the receivers that can help avert this problem. We also describe an evaluation of these schemes using simulation, and discuss a comparison of replicated-stream versus layered-encoding approaches.
{"title":"Bandwidth control for replicated-stream multicast video distribution","authors":"Xue Li, M. Ammar","doi":"10.1109/HPDC.1996.546206","DOIUrl":"https://doi.org/10.1109/HPDC.1996.546206","url":null,"abstract":"Real-time multicast video distribution is an important component of many multimedia applications. Our work addresses the fairness problem in feedback-controlled multicast video distribution systems over best effort networks (such as the Internet). We have proposed, implemented and experimented with a scheme called destination set grouping (DSG), where a source maintains a small number of video streams, all carrying the same video but each targeted at receivers with different capabilities. Each stream is feedback-controlled within prescribed limits by its group of receivers. Receivers may move among groups as their capabilities or the capabilities of the network paths leading to them change. In this paper, we focus on the potential for network overloading caused by the transmission of multiple replicated streams. We propose a number of mechanisms to be implemented at the source and the receivers that can help avert this problem. We also describe an evaluation of these schemes using simulation, and discuss a comparison of replicated-stream versus layered-encoding approaches.","PeriodicalId":267002,"journal":{"name":"Proceedings of 5th IEEE International Symposium on High Performance Distributed Computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1996-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124343674","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 : 1996-08-06DOI: 10.1109/HPDC.1996.546177
A. Grimshaw, W. Wulf
The coming of giga-bit networks makes possible the realization of a single nationwide virtual computer comprised of a variety of geographically distributed high-performance machines and workstations. To realize the potential that the physical infrastructure provides, software must be developed that is easy to use, supports a large degree of parallelism in the application code, and manages the complexity of the underlying physical system for the user. Legion is a metasystem project at the University of Virginia designed to provide users with a transparent interface to the available resources, both at the programming interface level as well as at the user level. Legion addresses issues such as parallelism, fault-tolerance, security, autonomy, heterogeneity, resource management and access transparency in a multi-language environment. In this paper, we present a high-level overview of Legion, its vision, objectives, a brief sketch of how some of those objectives will be met, and the current status of the project.
千兆比特网络的到来使得由分布在不同地理位置的高性能机器和工作站组成的单一全国性虚拟计算机的实现成为可能。为了实现物理基础设施提供的潜力，必须开发易于使用的软件，支持应用程序代码中的大量并行性，并为用户管理底层物理系统的复杂性。Legion是弗吉尼亚大学(University of Virginia)的一个元系统项目，旨在为用户提供一个访问可用资源的透明接口，无论是在编程接口级别还是在用户级别。Legion解决了多语言环境中的并行性、容错性、安全性、自主性、异构性、资源管理和访问透明度等问题。在本文中，我们将介绍Legion的高级概述，它的愿景，目标，如何实现这些目标的简要概述，以及项目的当前状态。
{"title":"Legion-a view from 50,000 feet","authors":"A. Grimshaw, W. Wulf","doi":"10.1109/HPDC.1996.546177","DOIUrl":"https://doi.org/10.1109/HPDC.1996.546177","url":null,"abstract":"The coming of giga-bit networks makes possible the realization of a single nationwide virtual computer comprised of a variety of geographically distributed high-performance machines and workstations. To realize the potential that the physical infrastructure provides, software must be developed that is easy to use, supports a large degree of parallelism in the application code, and manages the complexity of the underlying physical system for the user. Legion is a metasystem project at the University of Virginia designed to provide users with a transparent interface to the available resources, both at the programming interface level as well as at the user level. Legion addresses issues such as parallelism, fault-tolerance, security, autonomy, heterogeneity, resource management and access transparency in a multi-language environment. In this paper, we present a high-level overview of Legion, its vision, objectives, a brief sketch of how some of those objectives will be met, and the current status of the project.","PeriodicalId":267002,"journal":{"name":"Proceedings of 5th IEEE International Symposium on High Performance Distributed Computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1996-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126203979","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 : 1996-08-06DOI: 10.1109/HPDC.1996.546173
R. Aydt, A. Chien, D. Reed
The modest I/O configurations and file system limitations of many current high-performance systems preclude solution of problems with large I/O needs. I/O hardware and file system parallelism is the key to achieving high performance. We analyze the I/O behavior of several versions of two scientific applications on the Intel Paragon XP/S. The versions involve incremental application code enhancements across multiple releases of the operating system. Studying the evolution of I/O access patterns underscores the interplay between application access patterns and file system features. Our results show that both small and large request sizes are common, that at present, application developers must manually aggregate small requests to obtain high disk transfer rates, that concurrent file accesses are frequent, and that appropriate matching of the application access pattern and the file system access mode can significantly increase application I/O performance. Based on these results, we describe a set of file system design principles.
{"title":"I/O requirements of scientific applications: an evolutionary view","authors":"R. Aydt, A. Chien, D. Reed","doi":"10.1109/HPDC.1996.546173","DOIUrl":"https://doi.org/10.1109/HPDC.1996.546173","url":null,"abstract":"The modest I/O configurations and file system limitations of many current high-performance systems preclude solution of problems with large I/O needs. I/O hardware and file system parallelism is the key to achieving high performance. We analyze the I/O behavior of several versions of two scientific applications on the Intel Paragon XP/S. The versions involve incremental application code enhancements across multiple releases of the operating system. Studying the evolution of I/O access patterns underscores the interplay between application access patterns and file system features. Our results show that both small and large request sizes are common, that at present, application developers must manually aggregate small requests to obtain high disk transfer rates, that concurrent file accesses are frequent, and that appropriate matching of the application access pattern and the file system access mode can significantly increase application I/O performance. Based on these results, we describe a set of file system design principles.","PeriodicalId":267002,"journal":{"name":"Proceedings of 5th IEEE International Symposium on High Performance Distributed Computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1996-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125958331","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 : 1996-08-06DOI: 10.1109/HPDC.1996.546184
P. Sarkar, M. L. Bailey
Networks of workstations provide an economic solution for scalable computing because they do not require specialized components. Even though recent advances have shown that it is possible to obtain high bandwidth between applications, interconnect latency remains a serious concern. We present CNI, a cluster network interface that not only provides both low latency and high bandwidth but also efficiently supports multiple programming paradigms. This is done by functionally coupling the network adaptor board more closely to the CPU without changing the standard workstation architecture. CNI results in performance gains for applications, substantially reducing communication overhead and delay.
{"title":"CNI: a high-performance network interface for workstation clusters","authors":"P. Sarkar, M. L. Bailey","doi":"10.1109/HPDC.1996.546184","DOIUrl":"https://doi.org/10.1109/HPDC.1996.546184","url":null,"abstract":"Networks of workstations provide an economic solution for scalable computing because they do not require specialized components. Even though recent advances have shown that it is possible to obtain high bandwidth between applications, interconnect latency remains a serious concern. We present CNI, a cluster network interface that not only provides both low latency and high bandwidth but also efficiently supports multiple programming paradigms. This is done by functionally coupling the network adaptor board more closely to the CPU without changing the standard workstation architecture. CNI results in performance gains for applications, substantially reducing communication overhead and delay.","PeriodicalId":267002,"journal":{"name":"Proceedings of 5th IEEE International Symposium on High Performance Distributed Computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1996-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129608115","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：