用于跟踪处理器最小能量点的全数字片上异构传感器

Shu Hokimoto, Jun Shiomi, T. Ishihara, H. Onodera
{"title":"用于跟踪处理器最小能量点的全数字片上异构传感器","authors":"Shu Hokimoto, Jun Shiomi, T. Ishihara, H. Onodera","doi":"10.1109/ICMTS.2018.8383780","DOIUrl":null,"url":null,"abstract":"Dynamically scaling the supply voltage (VDD) and the threshold voltage (VTH) is one of the most effective approaches for reducing the energy consumption of processors. However, since the best pair of VDD and VTH, which minimizes the energy consumption of processors is strongly dependent on the operating condition such as an activity factor and a performance required for the processor, it is not trivial to find the best pair of the voltages at runtime when the operating condition widely varies. With all-digital on-chip heterogeneous sensors, we propose a simple runtime method to accurately identify the best pair of VDD and VTH, which minimizes the energy consumption of a processor under a specific operating condition which is determined by a process variation, an activity factor, and a performance requirement for the processor. Measured results for a 32-bit RISC processor integrating the heterogeneous sensors show that the proposed method successfully tracks the minimum energy operating point (i.e. the best pair of VDD and VTH) of the processor even in a case that the operating condition widely varies.","PeriodicalId":271839,"journal":{"name":"2018 IEEE International Conference on Microelectronic Test Structures (ICMTS)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"All-digital on-chip heterogeneous sensors for tracking the minimum energy point of processors\",\"authors\":\"Shu Hokimoto, Jun Shiomi, T. Ishihara, H. Onodera\",\"doi\":\"10.1109/ICMTS.2018.8383780\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Dynamically scaling the supply voltage (VDD) and the threshold voltage (VTH) is one of the most effective approaches for reducing the energy consumption of processors. However, since the best pair of VDD and VTH, which minimizes the energy consumption of processors is strongly dependent on the operating condition such as an activity factor and a performance required for the processor, it is not trivial to find the best pair of the voltages at runtime when the operating condition widely varies. With all-digital on-chip heterogeneous sensors, we propose a simple runtime method to accurately identify the best pair of VDD and VTH, which minimizes the energy consumption of a processor under a specific operating condition which is determined by a process variation, an activity factor, and a performance requirement for the processor. Measured results for a 32-bit RISC processor integrating the heterogeneous sensors show that the proposed method successfully tracks the minimum energy operating point (i.e. the best pair of VDD and VTH) of the processor even in a case that the operating condition widely varies.\",\"PeriodicalId\":271839,\"journal\":{\"name\":\"2018 IEEE International Conference on Microelectronic Test Structures (ICMTS)\",\"volume\":\"33 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-03-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2018 IEEE International Conference on Microelectronic Test Structures (ICMTS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICMTS.2018.8383780\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 IEEE International Conference on Microelectronic Test Structures (ICMTS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICMTS.2018.8383780","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2

摘要

动态调整电源电压(VDD)和阈值电压(VTH)是降低处理器能耗的最有效方法之一。然而,由于最大限度地减少处理器能耗的最佳VDD和VTH对强烈依赖于操作条件,例如处理器所需的活动因子和性能,因此在运行时,当操作条件变化很大时,找到最佳电压对并非易事。利用全数字片上异构传感器,我们提出了一种简单的运行时方法来准确识别最佳VDD和VTH对,从而最大限度地减少处理器在特定工作条件下的能耗,这是由工艺变化、活动因素和处理器的性能要求决定的。对集成异构传感器的32位RISC处理器的测量结果表明,即使在工作条件变化很大的情况下,该方法也能成功地跟踪处理器的最小能量工作点(即最佳VDD和VTH对)。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
All-digital on-chip heterogeneous sensors for tracking the minimum energy point of processors
Dynamically scaling the supply voltage (VDD) and the threshold voltage (VTH) is one of the most effective approaches for reducing the energy consumption of processors. However, since the best pair of VDD and VTH, which minimizes the energy consumption of processors is strongly dependent on the operating condition such as an activity factor and a performance required for the processor, it is not trivial to find the best pair of the voltages at runtime when the operating condition widely varies. With all-digital on-chip heterogeneous sensors, we propose a simple runtime method to accurately identify the best pair of VDD and VTH, which minimizes the energy consumption of a processor under a specific operating condition which is determined by a process variation, an activity factor, and a performance requirement for the processor. Measured results for a 32-bit RISC processor integrating the heterogeneous sensors show that the proposed method successfully tracks the minimum energy operating point (i.e. the best pair of VDD and VTH) of the processor even in a case that the operating condition widely varies.
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:481959085
Book学术官方微信