高性能处理器无用功耗的微架构估计

E. Musoll
{"title":"高性能处理器无用功耗的微架构估计","authors":"E. Musoll","doi":"10.1109/SBCCI.1999.802956","DOIUrl":null,"url":null,"abstract":"The purpose of this work is to evaluate the useless power consumption of a micro-processor that is, the power dissipated to perform those tasks that are not useful for the ultimate goal of committing instructions. This is a first-order estimation of the useless power consumption. A generic high-performance processor is divided in its basic micro-architecture blocks and the amount of useful and useless accesses to each of these blocks is estimated through simulations. The useless power consumption is further divided into useless power when: (a) executing instructions within a mispredicted path, and (b) then executing instructions that will be eventually committed by some of the block accesses performed by these instructions are not needed. The simulations performed indicate that if the useless power dissipation of a high-performance processor could be totally removed (at the cost of no IPC degradation), the overall processor power consumption would be reduced by as much as 65% compared to the same processor in which all the blocks are accessed every cycle.","PeriodicalId":342390,"journal":{"name":"Proceedings. XII Symposium on Integrated Circuits and Systems Design (Cat. No.PR00387)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1999-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Micro-architecture estimation of the useless power consumption of a high-performance processor\",\"authors\":\"E. Musoll\",\"doi\":\"10.1109/SBCCI.1999.802956\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The purpose of this work is to evaluate the useless power consumption of a micro-processor that is, the power dissipated to perform those tasks that are not useful for the ultimate goal of committing instructions. This is a first-order estimation of the useless power consumption. A generic high-performance processor is divided in its basic micro-architecture blocks and the amount of useful and useless accesses to each of these blocks is estimated through simulations. The useless power consumption is further divided into useless power when: (a) executing instructions within a mispredicted path, and (b) then executing instructions that will be eventually committed by some of the block accesses performed by these instructions are not needed. The simulations performed indicate that if the useless power dissipation of a high-performance processor could be totally removed (at the cost of no IPC degradation), the overall processor power consumption would be reduced by as much as 65% compared to the same processor in which all the blocks are accessed every cycle.\",\"PeriodicalId\":342390,\"journal\":{\"name\":\"Proceedings. XII Symposium on Integrated Circuits and Systems Design (Cat. No.PR00387)\",\"volume\":\"36 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1999-09-29\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings. XII Symposium on Integrated Circuits and Systems Design (Cat. No.PR00387)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/SBCCI.1999.802956\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings. XII Symposium on Integrated Circuits and Systems Design (Cat. No.PR00387)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SBCCI.1999.802956","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

这项工作的目的是评估微处理器的无用功耗,即执行那些对提交指令的最终目标无用的任务所消耗的功率。这是无用功耗的一阶估计。将一个通用的高性能处理器划分为基本的微体系结构块,并通过仿真估计每个块的有用和无用访问量。无用功耗进一步分为:(a)在错误预测的路径内执行指令,(b)执行这些指令执行的某些块访问最终会提交的指令是不需要的。进行的模拟表明,如果可以完全消除高性能处理器的无用功耗(以不降低IPC为代价),那么与每个周期访问所有块的相同处理器相比,处理器的总体功耗将减少多达65%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Micro-architecture estimation of the useless power consumption of a high-performance processor
The purpose of this work is to evaluate the useless power consumption of a micro-processor that is, the power dissipated to perform those tasks that are not useful for the ultimate goal of committing instructions. This is a first-order estimation of the useless power consumption. A generic high-performance processor is divided in its basic micro-architecture blocks and the amount of useful and useless accesses to each of these blocks is estimated through simulations. The useless power consumption is further divided into useless power when: (a) executing instructions within a mispredicted path, and (b) then executing instructions that will be eventually committed by some of the block accesses performed by these instructions are not needed. The simulations performed indicate that if the useless power dissipation of a high-performance processor could be totally removed (at the cost of no IPC degradation), the overall processor power consumption would be reduced by as much as 65% compared to the same processor in which all the blocks are accessed every cycle.
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