工作站容错网络的性能

Proceedings Fourth International Symposium on Parallel Architectures, Algorithms, and Networks (I-SPAN'99) Pub Date : 1999-06-23 DOI:10.1109/ISPAN.1999.778928

John Morris

{"title":"工作站容错网络的性能","authors":"John Morris","doi":"10.1109/ISPAN.1999.778928","DOIUrl":null,"url":null,"abstract":"Functional or dataflow models of computation enable a program's run-time system to determine which portions of a computation must be repeated when faults occur. Straightforward modifications to the run-time system of Cilk 2.0 (a threaded extension of C) enable a network-of-workstations parallel processing system to tolerate fail-stop faults of the individual processors or the network. It is shown in this paper that the overheads needed to provide this fault tolerance are mainly CPU cycles and memory, with very little additional network load being generated in the absence of faults. This makes it feasible to run long computations successfully on the typical networks of workstations found in large organisations, where ownership, control and distribution of the individual processors may be widely distributed.","PeriodicalId":157641,"journal":{"name":"Proceedings Fourth International Symposium on Parallel Architectures, Algorithms, and Networks (I-SPAN'99)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Performance of fault tolerant networks of workstations\",\"authors\":\"John Morris\",\"doi\":\"10.1109/ISPAN.1999.778928\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Functional or dataflow models of computation enable a program's run-time system to determine which portions of a computation must be repeated when faults occur. Straightforward modifications to the run-time system of Cilk 2.0 (a threaded extension of C) enable a network-of-workstations parallel processing system to tolerate fail-stop faults of the individual processors or the network. It is shown in this paper that the overheads needed to provide this fault tolerance are mainly CPU cycles and memory, with very little additional network load being generated in the absence of faults. This makes it feasible to run long computations successfully on the typical networks of workstations found in large organisations, where ownership, control and distribution of the individual processors may be widely distributed.\",\"PeriodicalId\":157641,\"journal\":{\"name\":\"Proceedings Fourth International Symposium on Parallel Architectures, Algorithms, and Networks (I-SPAN'99)\",\"volume\":\"36 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1999-06-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings Fourth International Symposium on Parallel Architectures, Algorithms, and Networks (I-SPAN'99)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ISPAN.1999.778928\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings Fourth International Symposium on Parallel Architectures, Algorithms, and Networks (I-SPAN'99)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISPAN.1999.778928","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 2

摘要

计算的功能模型或数据流模型使程序的运行时系统能够确定在发生错误时必须重复计算的哪一部分。对Cilk 2.0 (C的线程扩展)的运行时系统的直接修改使工作站网络并行处理系统能够容忍单个处理器或网络的故障停止。本文表明，提供这种容错所需的开销主要是CPU周期和内存，在没有故障的情况下，产生的额外网络负载非常少。这使得在大型组织中发现的典型工作站网络上成功运行长时间计算成为可能，在这些网络中，单个处理器的所有权、控制权和分布可能广泛分布。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Performance of fault tolerant networks of workstations

Functional or dataflow models of computation enable a program's run-time system to determine which portions of a computation must be repeated when faults occur. Straightforward modifications to the run-time system of Cilk 2.0 (a threaded extension of C) enable a network-of-workstations parallel processing system to tolerate fail-stop faults of the individual processors or the network. It is shown in this paper that the overheads needed to provide this fault tolerance are mainly CPU cycles and memory, with very little additional network load being generated in the absence of faults. This makes it feasible to run long computations successfully on the typical networks of workstations found in large organisations, where ownership, control and distribution of the individual processors may be widely distributed.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Proceedings Fourth International Symposium on Parallel Architectures, Algorithms, and Networks (I-SPAN'99)

自引率

0.00%

发文量