Power Distribution Network optimization for Associative Memories

L. Frontini, A. Stabile, V. Liberali
{"title":"Power Distribution Network optimization for Associative Memories","authors":"L. Frontini, A. Stabile, V. Liberali","doi":"10.1109/MOCAST.2017.7937633","DOIUrl":null,"url":null,"abstract":"Associative memories are massively parallel circuits which perform a parallel comparison between stored data and input data. When operated in parallel comparison mode, they require high current spikes (in the order of few amperes) at every clock edge, and the voltage drop due to current spikes can seriously affect the circuit operation. This paper proposes a method to enhance the power integrity, both at package level and at chip level. This work aims at avoiding “bounce” effects on supply voltages, and at keeping the supply voltage ripple below one hundred millivolts during the comparison mode. A technique to mitigate the voltage ripple consists in placing decoupling capacitors on the Power Delivery Network (PDN). This technique can be applied both at the chip level and at the package level. We show that this technique allows us to keep the power network impedance below 0.1 Ω within the relevant bandwidth of the circuit.","PeriodicalId":202381,"journal":{"name":"2017 6th International Conference on Modern Circuits and Systems Technologies (MOCAST)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 6th International Conference on Modern Circuits and Systems Technologies (MOCAST)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/MOCAST.2017.7937633","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

Abstract

Associative memories are massively parallel circuits which perform a parallel comparison between stored data and input data. When operated in parallel comparison mode, they require high current spikes (in the order of few amperes) at every clock edge, and the voltage drop due to current spikes can seriously affect the circuit operation. This paper proposes a method to enhance the power integrity, both at package level and at chip level. This work aims at avoiding “bounce” effects on supply voltages, and at keeping the supply voltage ripple below one hundred millivolts during the comparison mode. A technique to mitigate the voltage ripple consists in placing decoupling capacitors on the Power Delivery Network (PDN). This technique can be applied both at the chip level and at the package level. We show that this technique allows us to keep the power network impedance below 0.1 Ω within the relevant bandwidth of the circuit.
基于联想记忆的配电网络优化
联想存储器是大量并行电路,它在存储数据和输入数据之间执行并行比较。在并联比较模式下工作时,它们在每个时钟边缘都需要高电流尖峰(以几安培的顺序),并且由于电流尖峰引起的电压降会严重影响电路的工作。本文提出了一种从封装级和芯片级两方面提高电源完整性的方法。这项工作旨在避免电源电压的“反弹”效应,并在比较模式下保持电源电压纹波低于100毫伏。缓解电压纹波的一种技术是在输电网络(PDN)上放置去耦电容器。这种技术既可以应用于芯片级,也可以应用于封装级。我们表明,这种技术使我们能够在电路的相关带宽内保持电源网络阻抗低于0.1 Ω。
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