VDSM设计中用于全局互连的低延迟和低功耗混合插入方法

Shuming Chen, Xiangyuan Liu
{"title":"VDSM设计中用于全局互连的低延迟和低功耗混合插入方法","authors":"Shuming Chen, Xiangyuan Liu","doi":"10.1109/NOCS.2007.4","DOIUrl":null,"url":null,"abstract":"Current VLSI designs face a serious performance bottleneck due to reverse scaling of global interconnects as CMOS technology scales into VDSM regime. Interconnections techniques which decrease delay, power, and ensure signal integrity, play an important role in the growth of semiconductor industry into future generations. In this paper we present a novel hybrid insertion methodology for on-chip global interconnects. It takes advantage of repeaters and low-swing differential-signaling transceivers on driving long wires in different length, and optimally inserts them along the wires in order to decrease delay, power and gate area cost of interconnects. Simulation results using HSPICE for 0.18mum process showed that delay, power, delay-energy-product (EDP) and gate area cost were considerably decreased compared with other approaches available. Moreover, its computational technique is relatively easy and not limited to a specific low-swing differential-signaling transceiver. Therefore the methodology is very suitable for integration in EDA tool flow and beneficial for the reuse of low-swing differential-signaling transceivers","PeriodicalId":132772,"journal":{"name":"First International Symposium on Networks-on-Chip (NOCS'07)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2007-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"A Low-Latency and Low-Power Hybrid Insertion Methodology for Global Interconnects in VDSM Designs\",\"authors\":\"Shuming Chen, Xiangyuan Liu\",\"doi\":\"10.1109/NOCS.2007.4\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Current VLSI designs face a serious performance bottleneck due to reverse scaling of global interconnects as CMOS technology scales into VDSM regime. Interconnections techniques which decrease delay, power, and ensure signal integrity, play an important role in the growth of semiconductor industry into future generations. In this paper we present a novel hybrid insertion methodology for on-chip global interconnects. It takes advantage of repeaters and low-swing differential-signaling transceivers on driving long wires in different length, and optimally inserts them along the wires in order to decrease delay, power and gate area cost of interconnects. Simulation results using HSPICE for 0.18mum process showed that delay, power, delay-energy-product (EDP) and gate area cost were considerably decreased compared with other approaches available. Moreover, its computational technique is relatively easy and not limited to a specific low-swing differential-signaling transceiver. Therefore the methodology is very suitable for integration in EDA tool flow and beneficial for the reuse of low-swing differential-signaling transceivers\",\"PeriodicalId\":132772,\"journal\":{\"name\":\"First International Symposium on Networks-on-Chip (NOCS'07)\",\"volume\":\"27 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2007-05-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"First International Symposium on Networks-on-Chip (NOCS'07)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/NOCS.2007.4\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"First International Symposium on Networks-on-Chip (NOCS'07)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/NOCS.2007.4","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

摘要

当前的超大规模集成电路设计面临着严重的性能瓶颈,这是由于CMOS技术扩展到VDSM制度时全球互连的反向缩放。互连技术,降低延迟,功耗,并确保信号的完整性,在半导体产业的发展到未来几代发挥着重要作用。本文提出了一种用于片上全局互连的新型混合插入方法。它利用中继器和低摆幅差分信号收发器驱动不同长度的长导线,并将其沿导线最佳地插入,以降低互连的延迟、功耗和栅极面积成本。利用HSPICE对0.18 μ m过程进行了仿真,结果表明,与其他方法相比,延迟、功耗、延迟能量积(EDP)和栅极面积成本显著降低。此外,其计算技术相对简单,不局限于特定的低摆幅差分信号收发器。因此,该方法非常适合集成在EDA工具流中,有利于低摆幅差分信号收发器的重用
本文章由计算机程序翻译,如有差异,请以英文原文为准。
A Low-Latency and Low-Power Hybrid Insertion Methodology for Global Interconnects in VDSM Designs
Current VLSI designs face a serious performance bottleneck due to reverse scaling of global interconnects as CMOS technology scales into VDSM regime. Interconnections techniques which decrease delay, power, and ensure signal integrity, play an important role in the growth of semiconductor industry into future generations. In this paper we present a novel hybrid insertion methodology for on-chip global interconnects. It takes advantage of repeaters and low-swing differential-signaling transceivers on driving long wires in different length, and optimally inserts them along the wires in order to decrease delay, power and gate area cost of interconnects. Simulation results using HSPICE for 0.18mum process showed that delay, power, delay-energy-product (EDP) and gate area cost were considerably decreased compared with other approaches available. Moreover, its computational technique is relatively easy and not limited to a specific low-swing differential-signaling transceiver. Therefore the methodology is very suitable for integration in EDA tool flow and beneficial for the reuse of low-swing differential-signaling transceivers
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
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:604180095
Book学术官方微信