Dynamic low power management technique for decision directed inter-layer communication in three dimensional wireless network on chip

IF 1.7 4区 计算机科学 Q3 AUTOMATION & CONTROL SYSTEMS Automatika Pub Date : 2023-10-02 DOI:10.1080/00051144.2023.2261088
T. R. Dinesh Kumar, A. Karthikeyan
{"title":"Dynamic low power management technique for decision directed inter-layer communication in three dimensional wireless network on chip","authors":"T. R. Dinesh Kumar, A. Karthikeyan","doi":"10.1080/00051144.2023.2261088","DOIUrl":null,"url":null,"abstract":"3D ICs, a novel technology, might significantly impact multicore NoCs with hundreds or thousands of processing components on a single chip. Multiple 2D chips can be stacked vertically to create multiple active processing elements at various levels. Adding active device layers to 3D ICs can enhance system performance, increase functionality, and increase packing density. New architectural and IC technology advancements hinder energy-efficient design research. Achieving a balance between chip power and performance is crucial. This paper describes the “Dynamic Low Power Management Method in 3DWiNoC” (DLPM 3DWiNoC) architecture, which enables self-organized, centrally managed service management using Smart Master Agents. The approach utilizes SMA's ODA DD module for self-organized, centrally managed service management. To improve power regulation, data flow across vertical interconnects (TSVs) is reconfigured based on a dynamic evaluation of channel link use. SMA aims to reduce congestion by increasing connection utilization through high-frequency, bi-directional vertical channels via TSVs. The suggested system is modeled in MATLAB Simulink. Compared to 3D stacking, TSV stacking of vertical interconnects with the SMA method ensures low parasitic (latency and power) and higher bandwidth with higher vertical wire densities. Experimental results show that the proposed architecture decreases area overhead by 5%-7%, network latency by 12%-15%, and NoC power consumption by 15%-20% compared to the present multi-NoC design.","PeriodicalId":55412,"journal":{"name":"Automatika","volume":null,"pages":null},"PeriodicalIF":1.7000,"publicationDate":"2023-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Automatika","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1080/00051144.2023.2261088","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"AUTOMATION & CONTROL SYSTEMS","Score":null,"Total":0}
引用次数: 0

Abstract

3D ICs, a novel technology, might significantly impact multicore NoCs with hundreds or thousands of processing components on a single chip. Multiple 2D chips can be stacked vertically to create multiple active processing elements at various levels. Adding active device layers to 3D ICs can enhance system performance, increase functionality, and increase packing density. New architectural and IC technology advancements hinder energy-efficient design research. Achieving a balance between chip power and performance is crucial. This paper describes the “Dynamic Low Power Management Method in 3DWiNoC” (DLPM 3DWiNoC) architecture, which enables self-organized, centrally managed service management using Smart Master Agents. The approach utilizes SMA's ODA DD module for self-organized, centrally managed service management. To improve power regulation, data flow across vertical interconnects (TSVs) is reconfigured based on a dynamic evaluation of channel link use. SMA aims to reduce congestion by increasing connection utilization through high-frequency, bi-directional vertical channels via TSVs. The suggested system is modeled in MATLAB Simulink. Compared to 3D stacking, TSV stacking of vertical interconnects with the SMA method ensures low parasitic (latency and power) and higher bandwidth with higher vertical wire densities. Experimental results show that the proposed architecture decreases area overhead by 5%-7%, network latency by 12%-15%, and NoC power consumption by 15%-20% compared to the present multi-NoC design.
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
片上三维无线网络决策导向层间通信的动态低功耗管理技术
3D集成电路是一项新技术,可能会对单个芯片上有数百或数千个处理组件的多核noc产生重大影响。多个2D芯片可以垂直堆叠,以在不同级别创建多个活动处理元素。将有源器件层添加到3D ic中可以增强系统性能,增加功能并增加封装密度。新的建筑和集成电路技术的进步阻碍了节能设计的研究。实现芯片功率和性能之间的平衡至关重要。本文介绍了“3DWiNoC动态低功耗管理方法”(DLPM 3DWiNoC)架构,该架构使用智能主代理实现自组织、集中管理的服务管理。该方法利用SMA的ODA DD模块进行自组织、集中管理的服务管理。为了改善功率调节,垂直互连(tsv)之间的数据流基于通道链路使用的动态评估进行了重新配置。SMA旨在通过tsv增加高频双向垂直信道的连接利用率,从而减少拥塞。在MATLAB Simulink中对该系统进行了建模。与3D堆叠相比,采用SMA方法的垂直互连的TSV堆叠确保了低寄生(延迟和功耗)和更高的垂直线密度。实验结果表明,与现有的多NoC设计相比,该架构减少了5% ~ 7%的面积开销,减少了12% ~ 15%的网络延迟,减少了15% ~ 20%的NoC功耗。
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
Automatika
Automatika AUTOMATION & CONTROL SYSTEMS-ENGINEERING, ELECTRICAL & ELECTRONIC
CiteScore
4.00
自引率
5.30%
发文量
65
审稿时长
4.5 months
期刊介绍: AUTOMATIKA – Journal for Control, Measurement, Electronics, Computing and Communications is an international scientific journal that publishes scientific and professional papers in the field of automatic control, robotics, measurements, electronics, computing, communications and related areas. Click here for full Focus & Scope. AUTOMATIKA is published since 1960, and since 1991 by KoREMA - Croatian Society for Communications, Computing, Electronics, Measurement and Control, Member of IMEKO and IFAC.
期刊最新文献
Quasi Z source direct matrix converter based K- to three-phase wind energy conversion system using maximum constant boost current control modulation technique An adaptive multistage intrusion detection and prevention system in software defined networking environment SwinVNETR: Swin V-net Transformer with non-local block for volumetric MRI Brain Tumor Segmentation Dynamic control method of construction cost based on fuzzy neural network Data augmentation using a 1D-CNN model with MFCC/MFMC features for speech emotion recognition
×
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