Performance evaluation of InfiniBand with PCI Express

Jiuxing Liu, A. Mamidala, Abhinav Vishnu, D. Panda
{"title":"Performance evaluation of InfiniBand with PCI Express","authors":"Jiuxing Liu, A. Mamidala, Abhinav Vishnu, D. Panda","doi":"10.1109/CONECT.2004.1375193","DOIUrl":null,"url":null,"abstract":"We present an initial performance evaluation of InfiniBand HCAs (host channel adapters) from Mellanox with PCI Express interfaces. We compare the performance with HCAs using PCI-X interfaces. Our results show that InfiniBand HCAs with PCI Express can achieve significant performance benefits. Compared with HCAs using 64 bit/133 MHz PCI-X interfaces, they can achieve 20%-30% lower latency for small messages. The small message latency achieved with PCI Express is around 3.8 /spl mu/s, compared with the 5.0 /spl mu/s with PCI-X. For large messages, HCAs with PCI Express using a single port can deliver unidirectional bandwidth up to 968 MB/s and bidirectional bandwidth up to 1916 MB/s, which are, respectively, 1.24 and 2.02 times the peak bandwidths achieved by HCAs with PCI-X. When both the ports of the HCAs are activated, HCAs with PCI Express can deliver a peak unidirectional bandwidth of 1486 MB/s and aggregate bidirectional bandwidth up to 2729 MB/s, which are 1.93 and 2.88 times the peak bandwidths obtained using HCAs with PCI-X. PCI Express also improves performance at the MPI level. A latency of 4.6 /spl mu/s with PCI Express is achieved for small messages. And for large messages, unidirectional bandwidth of 1497 MB/s and bidirectional bandwidth of 2724 MB/s are observed.","PeriodicalId":224195,"journal":{"name":"Proceedings. 12th Annual IEEE Symposium on High Performance Interconnects","volume":"23 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2004-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"26","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings. 12th Annual IEEE Symposium on High Performance Interconnects","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CONECT.2004.1375193","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 26

Abstract

We present an initial performance evaluation of InfiniBand HCAs (host channel adapters) from Mellanox with PCI Express interfaces. We compare the performance with HCAs using PCI-X interfaces. Our results show that InfiniBand HCAs with PCI Express can achieve significant performance benefits. Compared with HCAs using 64 bit/133 MHz PCI-X interfaces, they can achieve 20%-30% lower latency for small messages. The small message latency achieved with PCI Express is around 3.8 /spl mu/s, compared with the 5.0 /spl mu/s with PCI-X. For large messages, HCAs with PCI Express using a single port can deliver unidirectional bandwidth up to 968 MB/s and bidirectional bandwidth up to 1916 MB/s, which are, respectively, 1.24 and 2.02 times the peak bandwidths achieved by HCAs with PCI-X. When both the ports of the HCAs are activated, HCAs with PCI Express can deliver a peak unidirectional bandwidth of 1486 MB/s and aggregate bidirectional bandwidth up to 2729 MB/s, which are 1.93 and 2.88 times the peak bandwidths obtained using HCAs with PCI-X. PCI Express also improves performance at the MPI level. A latency of 4.6 /spl mu/s with PCI Express is achieved for small messages. And for large messages, unidirectional bandwidth of 1497 MB/s and bidirectional bandwidth of 2724 MB/s are observed.
采用 PCI Express 的 InfiniBand 性能评估
我们介绍了对带有 PCI Express 接口的 Mellanox InfiniBand HCA(主机通道适配器)的初步性能评估。我们将其性能与使用 PCI-X 接口的 HCA 进行了比较。我们的结果表明,采用 PCI Express 的 InfiniBand HCA 可以实现显著的性能优势。与使用 64 位/133 MHz PCI-X 接口的 HCA 相比,它们可以将小信息的延迟时间降低 20%-30%。PCI Express 实现的小信息延迟约为 3.8 /spl mu/s,而 PCI-X 为 5.0 /spl mu/s。对于大型信息,使用单端口 PCI Express 的 HCA 可提供高达 968 MB/s 的单向带宽和高达 1916 MB/s 的双向带宽,分别是使用 PCI-X 的 HCA 峰值带宽的 1.24 倍和 2.02 倍。当 HCA 的两个端口都激活时,带 PCI Express 的 HCA 可提供 1486 MB/s 的峰值单向带宽和高达 2729 MB/s 的总双向带宽,分别是带 PCI-X 的 HCA 峰值带宽的 1.93 倍和 2.88 倍。PCI Express 还提高了 MPI 级别的性能。使用 PCI Express 时,小信息的延迟为 4.6 /spl mu/s。对于大型信息,单向带宽为 1497 MB/s,双向带宽为 2724 MB/s。
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 求助全文
来源期刊
自引率
0.00%
发文量
0
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信