Communication optimization for thermal reliable many-core systems: work-in-progress

Weichen Liu, Lei Yang, Weiwen Jiang, Nan Guan
{"title":"Communication optimization for thermal reliable many-core systems: work-in-progress","authors":"Weichen Liu, Lei Yang, Weiwen Jiang, Nan Guan","doi":"10.1145/3125502.3125539","DOIUrl":null,"url":null,"abstract":"System-level thermal management techniques normally map applications on non-adjacent cores to guarantee the safe temperature in many-core systems, while the communication efficiency will be oppositely affected by long-distance data transmission over conventional Network-on-Chips (NoC). SMART NoC has enabled single-cycle multi-hop bypass channels between distant cores, which can significantly reduce inter-processor communication latency. However, communication efficiency of SMART will be significantly diminished by express bypass break due to communication conflict. In order to achieve communication optimization with guaranteed system thermal reliability, we propose a dynamic reconfiguration method for logical interconnection topology through task mapping on top of SMART NoC. Active cores are physically decentralized on chip for better heat dissipation, while communication overhead can be reduced by minimized communication conflict and maximized bypass routing. Applicability and effectiveness of the proposed technique can be improved with significant achievements in reducing communication overhead and improving application performance, compared with state-of-the-art techniques.","PeriodicalId":350509,"journal":{"name":"Proceedings of the Twelfth IEEE/ACM/IFIP International Conference on Hardware/Software Codesign and System Synthesis Companion","volume":"16 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the Twelfth IEEE/ACM/IFIP International Conference on Hardware/Software Codesign and System Synthesis Companion","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3125502.3125539","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

System-level thermal management techniques normally map applications on non-adjacent cores to guarantee the safe temperature in many-core systems, while the communication efficiency will be oppositely affected by long-distance data transmission over conventional Network-on-Chips (NoC). SMART NoC has enabled single-cycle multi-hop bypass channels between distant cores, which can significantly reduce inter-processor communication latency. However, communication efficiency of SMART will be significantly diminished by express bypass break due to communication conflict. In order to achieve communication optimization with guaranteed system thermal reliability, we propose a dynamic reconfiguration method for logical interconnection topology through task mapping on top of SMART NoC. Active cores are physically decentralized on chip for better heat dissipation, while communication overhead can be reduced by minimized communication conflict and maximized bypass routing. Applicability and effectiveness of the proposed technique can be improved with significant achievements in reducing communication overhead and improving application performance, compared with state-of-the-art techniques.
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
热可靠多核系统的通信优化:正在进行的工作
系统级热管理技术通常将应用映射到非相邻核上,以保证多核系统的安全温度,而传统的片上网络(NoC)的远程数据传输将影响通信效率。SMART NoC启用了远核之间的单周期多跳旁路通道,可以显着减少处理器间通信延迟。但是,由于通信冲突导致的快速旁路中断会大大降低SMART的通信效率。为了在保证系统热可靠性的前提下实现通信优化,提出了一种基于SMART NoC的任务映射逻辑互连拓扑动态重构方法。主动核心物理上分散在芯片上,以获得更好的散热,而通信开销可以通过最小化通信冲突和最大化旁路路由来降低。与现有技术相比,该技术在降低通信开销和提高应用程序性能方面取得了显著成就,从而提高了其适用性和有效性。
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
3D nanosystems enable embedded abundant-data computing: special session paper Remote detection of unauthorized activity via spectral analysis: work-in-progress Exploring fast and slow memories in HMP core types: work-in-progress An efficient hardware design for cerebellar models using approximate circuits: special session paper DOVE: pinpointing firmware security vulnerabilities via symbolic control flow assertion mining (work-in-progress)
×
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