Fault-Tolerant Distributed Shared Memory on a Broadcast-Based Interconnection Network.pdf

下载文档

4
0
约6.04万字
约 19页
2017-04-13 发布于江苏
举报
版权申诉
保障服务

Fault-Tolerant Distributed Shared Memory on a Broadcast-Based Interconnection Network.pdf

1、本文档共19页，可阅读全部内容。
2、原创力文档（book118）网站文档一经付费（服务费），不意味着购买了该文档的版权，仅供个人/单位学习、研究之用，不得用于商业用途，未经授权，严禁复制、发行、汇编、翻译或者网络传播等，侵权必究。
3、本站所有内容均由合作方或网友上传，本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺！文档内容仅供研究参考，付费前请自行鉴别。如您付费，意味着您自己接受本站规则且自行承担风险，本站不退款、不进行额外附加服务；查看《如何避免下载的几个坑》。如果您已付费下载过本站文档，您可以点击这里二次下载。
4、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等，请点击“版权申诉”（推荐），也可以打举报电话：400-050-0827(电话支持时间：9:00-18:30)。

Fault-Tolerant Distributed Shared Memory on a Broadcast-Based Interconnection Network

C. Katsinis is with the Department of Electrical and Computer Engineering, Drexel University, Philadelphia, PA 19104. E-mail: katsinis@ D. Hecht is with Rydal Research and Development, Rydal, PA 19046. E-mail: diana@ Preliminary versions of this paper were presented at the IEEE Workshops On Fault-Tolerant Parallel and Distributed Systems, April 2002 and 2003. Fault-tolerant Distributed Shared Memory on a Broadcast-based Architecture Constantine Katsinis, Member, IEEE Computer Society and Diana Hecht, Member, IEEE Computer Society Abstract - - Due to advances in fiber-optics and VLSI technology, interconnection networks that allow multiple simultaneous broadcasts are becoming feasible. Distributed-shared-memory implementations on such networks promise high performance even for applications with small granularity. This paper presents the architecture of one such implementation, called the Simultaneous Optical Multiprocessor Exchange Bus, and examines the performance of augmented DSM protocols that exploit the natural duplication of data to maintain a recovery memory in each processing node and provide basic fault tolerance. Simulation results show that the additional data duplication necessary to create fault-tolerant DSM causes no reduction in system performance during normal operation and eliminates most of the overhead at checkpoint creation. Under certain conditions, data blocks that are duplicated to maintain the recovery memory are utilized by the underlying DSM protocol, reducing network traffic, and increasing the processor utilization significantly. Index Terms: multiprocessors, distributed-shared-memory, fault-tolerance 1 INTRODUCTION1 Distributed-shared-memory (DSM) is a common programming model supported by multiprocessor systems, along with message passing, and data parallel processing. DSM systems offer the application programmer a shared-data model closely related to sequential programming, and reduce the complexity of developing distributed applicatio