Performance maximization of 3D-stacked cache memory on DVFS-enabled processor

K. Kang, Jongpil Jung, C. Kyung
{"title":"Performance maximization of 3D-stacked cache memory on DVFS-enabled processor","authors":"K. Kang, Jongpil Jung, C. Kyung","doi":"10.1109/SOCDC.2010.5682975","DOIUrl":null,"url":null,"abstract":"3D integration increases chip integration density, reduces wire length, wire delay and power consumption on wires. However, increased power density causes increase of temperature, which results in the increase of leakage power consumption and performance degradation. In this paper, we propose a solution to compromise these issues on stacking cache memory on a processor core. Experimental results have shown that the proposed method yields, on the average, 16% performance improvement in terms of instructions per second compared to conventional method. The proposed method also reduces energy consumption by 20% on average, in terms of energy per instruction.","PeriodicalId":380183,"journal":{"name":"2010 International SoC Design Conference","volume":"41 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2010 International SoC Design Conference","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SOCDC.2010.5682975","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2

Abstract

3D integration increases chip integration density, reduces wire length, wire delay and power consumption on wires. However, increased power density causes increase of temperature, which results in the increase of leakage power consumption and performance degradation. In this paper, we propose a solution to compromise these issues on stacking cache memory on a processor core. Experimental results have shown that the proposed method yields, on the average, 16% performance improvement in terms of instructions per second compared to conventional method. The proposed method also reduces energy consumption by 20% on average, in terms of energy per instruction.
在启用dvfs的处理器上实现3d堆叠高速缓存的性能最大化
3D集成增加了芯片集成密度,减少了导线长度、导线延迟和导线功耗。但是,功率密度的增加会引起温度的升高,从而导致泄漏功耗的增加和性能的下降。在本文中,我们提出了一种解决方案来解决这些问题,即在处理器核心上堆叠高速缓存存储器。实验结果表明,与传统方法相比,该方法的平均每秒指令数提高了16%。就每条指令的能量而言,所提出的方法还平均减少了20%的能量消耗。
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 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:604180095
Book学术官方微信