Fast scheduling based on iterative parallel wavelength matching for a multi-wavelength ring network-on-chip

I. Cerutti, N. Andriolli, P. Pintus, S. Faralli, F. Gambini, O. Liboiron-Ladouceur, P. Castoldi
{"title":"Fast scheduling based on iterative parallel wavelength matching for a multi-wavelength ring network-on-chip","authors":"I. Cerutti, N. Andriolli, P. Pintus, S. Faralli, F. Gambini, O. Liboiron-Ladouceur, P. Castoldi","doi":"10.1109/ONDM.2015.7127295","DOIUrl":null,"url":null,"abstract":"In synchronous networks-on-chip (NoC), scheduling of packet transmission is required for achieving high throughput, low latency and good fairness, while avoiding packet collisions. Efficient algorithms exist for rearrangeably non-blocking NoC. However, when realized with integrated optical devices, NoC are typically arranged in topologies that are blocking if a single wavelength is used. Mitigation of the blocking behavior is then achieved by exploiting the wavelength domain, which requires however a novel scheduling paradigm. This paper presents an integrated optical NoC based on a ring topology and realized with multiple resonating microrings (MMR). Scheduling in MMR architecture comprises the conventional matching sub-problem along with wavelength assignment sub-problem, which accounts for the additional constraints due to the wavelength domain. A novel scheduling algorithm based on iSLIP algorithm is proposed for jointly addressing both sub-problems. The iterative Parallel Wavelength Matching (iPWM) algorithm achieves performance similar to a two-step scheduler based on sequential iSLIP and first-fit wavelength assignment, but with a computational complexity lower and independent of the number of wavelengths.","PeriodicalId":282743,"journal":{"name":"2015 International Conference on Optical Network Design and Modeling (ONDM)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2015-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2015 International Conference on Optical Network Design and Modeling (ONDM)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ONDM.2015.7127295","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 7

Abstract

In synchronous networks-on-chip (NoC), scheduling of packet transmission is required for achieving high throughput, low latency and good fairness, while avoiding packet collisions. Efficient algorithms exist for rearrangeably non-blocking NoC. However, when realized with integrated optical devices, NoC are typically arranged in topologies that are blocking if a single wavelength is used. Mitigation of the blocking behavior is then achieved by exploiting the wavelength domain, which requires however a novel scheduling paradigm. This paper presents an integrated optical NoC based on a ring topology and realized with multiple resonating microrings (MMR). Scheduling in MMR architecture comprises the conventional matching sub-problem along with wavelength assignment sub-problem, which accounts for the additional constraints due to the wavelength domain. A novel scheduling algorithm based on iSLIP algorithm is proposed for jointly addressing both sub-problems. The iterative Parallel Wavelength Matching (iPWM) algorithm achieves performance similar to a two-step scheduler based on sequential iSLIP and first-fit wavelength assignment, but with a computational complexity lower and independent of the number of wavelengths.
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
基于迭代并行波长匹配的多波长环形片上网络快速调度
在同步片上网络(NoC)中,为了实现高吞吐量、低延迟和良好的公平性,同时避免分组冲突,需要对分组传输进行调度。对于可重新排列的非阻塞NoC,存在有效的算法。然而,当集成光学器件实现时,如果使用单一波长,NoC通常排列在拓扑结构中。然后通过利用波长域来缓解阻塞行为,但这需要一种新的调度范式。本文提出了一种基于环形拓扑结构的集成光学NoC,并采用多个谐振微环(MMR)实现。MMR体系结构中的调度包括传统的匹配子问题和波长分配子问题,波长分配子问题考虑了波长域的附加约束。提出了一种新的基于iSLIP算法的调度算法,用于联合解决这两个子问题。迭代并行波长匹配(iPWM)算法的性能与基于顺序iSLIP和首次拟合波长分配的两步调度器相似,但计算复杂度较低且与波长数无关。
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
Innovative tracking system for next generation FSO systems under massive earthquakes Blocking performance of cost efficient integrated OTN/WDM metropolitan networks in static traffic scenario Exploring the effects of physical layer parameters in WDM based fixed and flexible-grid networks Virtual PON assignment for fixed-mobile convergent access-aggregation networks Where do we stand and where are we heading in making NG-PONs more energy efficient ?
×
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