Efficient virtual interface architecture (VIA) support for the IBM SP switch-connected NT clusters

M. Banikazemi, V. Moorthy, D. Panda, L. Herger, B. Abali
{"title":"Efficient virtual interface architecture (VIA) support for the IBM SP switch-connected NT clusters","authors":"M. Banikazemi, V. Moorthy, D. Panda, L. Herger, B. Abali","doi":"10.1109/IPDPS.2000.845962","DOIUrl":null,"url":null,"abstract":"The IBM SP Switch-Connected NT cluster is one the newest clustering platforms available. In this paper, we discuss an experimental implementation of the Virtual Interface Architecture for this platform. We discuss different design issues involved in this implementation. In particular, we explain how the virtual-to-physical address translation can be implemented efficiently with a minimum Network Interface Card (NIC) memory requirement. We show how caching the VIA descriptors on the NIC can reduce the communication latency. We also present an efficient scheme for implementing the VIA door bells without any hardware support. A comprehensive performance evaluation study of the implementation is provided. The performance of the implemented VIA surpasses that of other existing software implementations of the VIA and is comparable to that of a hardware VIA implementation. The peak measured bandwidth for our system is observed to be 101.4 MBytes/s and the one-way latency for short messages is 18.2 microseconds. It is to be noted that the VIA implementation presented in this paper is not a part of any IBM product and no assumptions should be made regarding its availability as a product in the future.","PeriodicalId":206541,"journal":{"name":"Proceedings 14th International Parallel and Distributed Processing Symposium. IPDPS 2000","volume":"142 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2000-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"30","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings 14th International Parallel and Distributed Processing Symposium. IPDPS 2000","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IPDPS.2000.845962","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 30

Abstract

The IBM SP Switch-Connected NT cluster is one the newest clustering platforms available. In this paper, we discuss an experimental implementation of the Virtual Interface Architecture for this platform. We discuss different design issues involved in this implementation. In particular, we explain how the virtual-to-physical address translation can be implemented efficiently with a minimum Network Interface Card (NIC) memory requirement. We show how caching the VIA descriptors on the NIC can reduce the communication latency. We also present an efficient scheme for implementing the VIA door bells without any hardware support. A comprehensive performance evaluation study of the implementation is provided. The performance of the implemented VIA surpasses that of other existing software implementations of the VIA and is comparable to that of a hardware VIA implementation. The peak measured bandwidth for our system is observed to be 101.4 MBytes/s and the one-way latency for short messages is 18.2 microseconds. It is to be noted that the VIA implementation presented in this paper is not a part of any IBM product and no assumptions should be made regarding its availability as a product in the future.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
对IBM SP交换机连接的NT集群的高效虚拟接口体系结构(VIA)支持
IBM SP Switch-Connected NT集群是可用的最新集群平台之一。本文讨论了虚拟接口架构在该平台上的实验实现。我们将讨论此实现中涉及的不同设计问题。特别是,我们解释了如何在最小的网络接口卡(NIC)内存需求下有效地实现虚拟到物理地址的转换。我们将展示如何在NIC上缓存VIA描述符来减少通信延迟。我们还提出了一种无需硬件支持即可实现VIA门铃的有效方案。对该方案的实施进行了全面的绩效评价研究。实现的VIA的性能超过了其他现有的软件实现的VIA,并且与硬件实现的VIA相当。我们的系统测量到的峰值带宽为101.4 mb /s,短消息的单向延迟为18.2微秒。值得注意的是,本文中介绍的VIA实现不是任何IBM产品的一部分,并且不应该对其将来作为产品的可用性做出任何假设。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Predicting performance on SMPs. A case study: the SGI Power Challenge An optimal parallel algorithm for computing moments on arrays with reconfigurable optical buses Parallel performance study of Monte Carlo photon transport code on shared-, distributed-, and distributed-shared-memory architectures Replicating the contents of a WWW multimedia repository to minimize download time Efficiency of dynamic load balancing based on permanent cells for parallel molecular dynamics simulation
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1