Power shifting in Thrifty Interconnection Network

Jian Li, Wei Huang, C. Lefurgy, Lixin Zhang, W. Denzel, Richard R. Treumann, Kun Wang
{"title":"Power shifting in Thrifty Interconnection Network","authors":"Jian Li, Wei Huang, C. Lefurgy, Lixin Zhang, W. Denzel, Richard R. Treumann, Kun Wang","doi":"10.1109/HPCA.2011.5749725","DOIUrl":null,"url":null,"abstract":"This paper presents two complementary techniques to manage the power consumption of large-scale systems with a packet-switched interconnection network. First, we propose Thrifty Interconnection Network (TIN), where the network links are activated and de-activated dynamically with little or no overhead by using inherent system events to timely trigger link activation or de-activation. Second, we propose Network Power Shifting (NPS) that dynamically shifts the power budget between the compute nodes and their corresponding network components. TIN activates and trains the links in the interconnection network, just-in-time before the network communication is about to happen, and thriftily puts them into a low-power mode when communication is finished, hence reducing unnecessary network power consumption. Furthermore, the compute nodes can absorb the extra power budget shifted from its attached network components and increase their processor frequency for higher performance with NPS. Our simulation results on a set of real-world workload traces show that TIN can achieve on average 60% network power reduction, with the support of only one low-power mode. When NPS is enabled, the two together can achieve 12% application performance improvement and 13% overall system energy reduction. Further performance improvement is possible if the compute nodes can speed up more and fully utilize the extra power budget reinvested from the thrifty network with more aggressive cooling support.","PeriodicalId":126976,"journal":{"name":"2011 IEEE 17th International Symposium on High Performance Computer Architecture","volume":"11 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2011-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"34","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2011 IEEE 17th International Symposium on High Performance Computer Architecture","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/HPCA.2011.5749725","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 34

Abstract

This paper presents two complementary techniques to manage the power consumption of large-scale systems with a packet-switched interconnection network. First, we propose Thrifty Interconnection Network (TIN), where the network links are activated and de-activated dynamically with little or no overhead by using inherent system events to timely trigger link activation or de-activation. Second, we propose Network Power Shifting (NPS) that dynamically shifts the power budget between the compute nodes and their corresponding network components. TIN activates and trains the links in the interconnection network, just-in-time before the network communication is about to happen, and thriftily puts them into a low-power mode when communication is finished, hence reducing unnecessary network power consumption. Furthermore, the compute nodes can absorb the extra power budget shifted from its attached network components and increase their processor frequency for higher performance with NPS. Our simulation results on a set of real-world workload traces show that TIN can achieve on average 60% network power reduction, with the support of only one low-power mode. When NPS is enabled, the two together can achieve 12% application performance improvement and 13% overall system energy reduction. Further performance improvement is possible if the compute nodes can speed up more and fully utilize the extra power budget reinvested from the thrifty network with more aggressive cooling support.
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
节约型互联网络中的权力转移
本文提出了两种互补的技术来管理具有分组交换互连网络的大型系统的功耗。首先,我们提出节俭互连网络(TIN),其中网络链路通过使用固有的系统事件及时触发链路激活或去激活,以很少或没有开销的方式动态激活和去激活。其次,我们提出了网络功率转移(NPS),它在计算节点和相应的网络组件之间动态地转移功率预算。TIN在网络通信即将发生之前及时激活和训练互联网络中的链路,并在通信结束时节省地将其置于低功耗模式,从而减少不必要的网络功耗。此外,计算节点可以吸收其附加网络组件转移的额外功率预算,并通过NPS提高其处理器频率以获得更高的性能。我们对一组实际工作负载跟踪的仿真结果表明,在仅支持一种低功耗模式的情况下,TIN可以实现平均60%的网络功耗降低。当启用NPS时,两者可以共同实现12%的应用性能提升和13%的整体系统能耗降低。如果计算节点可以更快地加速,并充分利用节省网络再投资的额外电力预算,并提供更积极的冷却支持,则进一步的性能改进是可能的。
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
Safe and efficient supervised memory systems Keynote address II: How's the parallel computing revolution going? A case for guarded power gating for multi-core processors Fg-STP: Fine-Grain Single Thread Partitioning on Multicores A quantitative performance analysis model for GPU architectures
×
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