Gallium arsenide technology for low-power, high performance processor cores

S. Lachowicz, K. Eshraghian, J.F. Lopez
{"title":"Gallium arsenide technology for low-power, high performance processor cores","authors":"S. Lachowicz, K. Eshraghian, J.F. Lopez","doi":"10.1109/COMMAD.1998.791684","DOIUrl":null,"url":null,"abstract":"Recent developments in multimedia computing and communications have lead to rapid increase in performance requirements for the underlying VLSI technology which manifests itself in the development of new semiconductor materials as well as refinements in the existing ones. Not only are the circuits required to operate faster and dissipate less power, especially for portable applications, but integration of optics, i.e. image display and light detection functionality together with sophisticated signal processing in one chip becomes now a necessity and reality at the same time. The concept of personal interactive mobile multimedia communicators (M/sup 3/C) has lead to the idea of an intelligent pixel (IP) array which is effectively a video camera, a miniature display screen, and an advanced DSP processor in one device. For ultra-fast systems a considerable part of power is dissipated within a clock generation and distribution system. At the same time, at Gigahertz frequencies the clock skew becomes the factor limiting the speed of the system. This paper presents an outline of the intelligent pixel architecture and presents a detailed design methodology for highly pipelined, self-timed systems suitable for multimedia applications using Gallium Arsenide MESFET as the base technology implementation of latched logic design style (PDLL, LCFL). The use of latched logic together with the absence of the global clock provides for low power dissipation while maintaining very high speed of the system.","PeriodicalId":300064,"journal":{"name":"1998 Conference on Optoelectronic and Microelectronic Materials and Devices. Proceedings (Cat. No.98EX140)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1998-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"1998 Conference on Optoelectronic and Microelectronic Materials and Devices. Proceedings (Cat. No.98EX140)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/COMMAD.1998.791684","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

Recent developments in multimedia computing and communications have lead to rapid increase in performance requirements for the underlying VLSI technology which manifests itself in the development of new semiconductor materials as well as refinements in the existing ones. Not only are the circuits required to operate faster and dissipate less power, especially for portable applications, but integration of optics, i.e. image display and light detection functionality together with sophisticated signal processing in one chip becomes now a necessity and reality at the same time. The concept of personal interactive mobile multimedia communicators (M/sup 3/C) has lead to the idea of an intelligent pixel (IP) array which is effectively a video camera, a miniature display screen, and an advanced DSP processor in one device. For ultra-fast systems a considerable part of power is dissipated within a clock generation and distribution system. At the same time, at Gigahertz frequencies the clock skew becomes the factor limiting the speed of the system. This paper presents an outline of the intelligent pixel architecture and presents a detailed design methodology for highly pipelined, self-timed systems suitable for multimedia applications using Gallium Arsenide MESFET as the base technology implementation of latched logic design style (PDLL, LCFL). The use of latched logic together with the absence of the global clock provides for low power dissipation while maintaining very high speed of the system.
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
用于低功耗、高性能处理器核心的砷化镓技术
多媒体计算和通信的最新发展导致对VLSI底层技术的性能要求迅速提高,这体现在新半导体材料的开发以及对现有半导体材料的改进上。不仅要求电路运行速度更快,功耗更低,特别是对于便携式应用,而且光学集成,即图像显示和光检测功能以及在一个芯片上进行复杂的信号处理,现在成为必要和现实。个人交互式移动多媒体通信(M/sup /C)的概念导致了智能像素(IP)阵列的想法,该阵列有效地集摄像机、微型显示屏和先进的DSP处理器于一体。对于超高速系统,相当一部分功率在时钟产生和分配系统中耗散。同时,在千兆赫频率下,时钟偏差成为限制系统速度的因素。本文提出了智能像素架构的概述,并提出了一种详细的设计方法,用于高度流水线,自定时系统,适用于多媒体应用,使用砷化镓MESFET作为锁存逻辑设计风格(PDLL, LCFL)的基本技术实现。锁存逻辑的使用以及全局时钟的缺失提供了低功耗,同时保持系统的非常高的速度。
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
InGaP/GaAs resonant-tunneling transistor (RTT) Gallium arsenide technology for low-power, high performance processor cores Thick-film gas and humidity sensing array based on semiconducting metal oxides Compact modeling of high-frequency, small-dimension bipolar transistors Magneto-transport studies in AlGaN/GaN MODFETs
×
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