Temperature-aware microarchitecture

Author:

Skadron Kevin1,Stan Mircea R.1,Huang Wei1,Velusamy Sivakumar1,Sankaranarayanan Karthik1,Tarjan David1

Affiliation:

1. University of Virginia, Charlottesville, VA

Abstract

With power density and hence cooling costs rising exponentially, processor packaging can no longer be designed for the worst case, and there is an urgent need for runtime processor-level techniques that can regulate operating temperature when the package's capacity is exceeded. Evaluating such techniques, however, requires a thermal model that is practical for architectural studies.This paper describes HotSpot, an accurate yet fast model based on an equivalent circuit of thermal resistances and capacitances that correspond to microarchitecture blocks and essential aspects of the thermal package. Validation was performed using finite-element simulation. The paper also introduces several effective methods for dynamic thermal management (DTM): "temperature-tracking" frequency scaling, localized toggling, and migrating computation to spare hardware units. Modeling temperature at the microarchitecture level also shows that power metrics are poor predictors of temperature, and that sensor imprecision has a substantial impact on the performance of DTM.

Publisher

Association for Computing Machinery (ACM)

Reference28 articles.

1. High-Accuracy CMOS Smart Temperature Sensors

2. P. Bannon. Personal communication Sep. 2002.]] P. Bannon. Personal communication Sep. 2002.]]

3. Design challenges of technology scaling

4. Wattch

Cited by 62 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Thermal Map Dataset for Commercial Multi/Many Core CPU/GPU/TPU;Proceedings of the 2024 ACM/IEEE International Symposium on Machine Learning for CAD;2024-09-09

2. Cluster Based Adaptive Multi-Voltage Scaling Dynamic Task Mapping for WNoC and HWNoC;2024-06-05

3. Hybrid Model-Based Thermal Analysis Methodology for Integrated Circuits;2024 2nd International Symposium of Electronics Design Automation (ISEDA);2024-05-10

4. A Learning-based Control Scheme for MTJ-based Non-volatile Flip-Flops;IPSJ Transactions on System and LSI Design Methodology;2024

5. TREAD-M3D: Temperature-Aware DNN Accelerators for Monolithic 3-D Mobile Systems;IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems;2023-12

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3