电子学报 ›› 2016, Vol. 44 ›› Issue (6): 1272-1278.DOI: 10.3969/j.issn.0372-2112.2016.06.002

• 学术论文 • 上一篇    下一篇

多处理器片上系统中一种结合二阶导数的温度预测模型

魏琳1, 周磊1, 吴宁2, 杨睛1   

  1. 1. 扬州大学信息工程学院, 江苏扬州 225000;
    2. 南京航空航天大学电子信息工程学院, 江苏南京 210016
  • 收稿日期:2014-11-20 修回日期:2015-01-28 出版日期:2016-06-25 发布日期:2016-06-25
  • 通讯作者: 周磊
  • 作者简介:魏琳 女,1990年10月出生于江苏省靖江市.2013年获得扬州大学广陵学院学士学位.现为扬州大学信息工程学院硕士研究生.主要研究方向为电子系统集成和专用集成电路设计.E-mail:elitals@163.com
  • 基金资助:

    国家自然科学基金(No.61376025,No.61301111);江苏省高校自然科学基金(No.13KJB510039);江苏省普通高校研究生科研实践计划项目(No.SJZZ_0182)

A Predictive Thermal Model Combined with the Second Derivative for Multiprocessor System-on-Chips

WEI Lin1, ZHOU Lei1, WU Ning2, YANG Jing1   

  1. 1. College of Information Engineering, Yangzhou University, Yanghzou, Jiangsu 225000, China;
    2. College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, Jiangsu 210016, China
  • Received:2014-11-20 Revised:2015-01-28 Online:2016-06-25 Published:2016-06-25

摘要:

区域温度预测是多处理器片上系统(MultiProcessor System-on-Chips,MPSoCs)高效散热的基础.本文以RC热传导(Thermal Resistance and Capacitance,Thermal RC)模型为基础,结合二阶导数提出了一种温度预测模型.该模型不仅可以在较低的运算复杂度下准确预测温度,而且能在固定的预测误差率范围内拓宽预测时间长度,进而减少模型在实际运行中被调用的次数,降低额外功耗.实验结果表明,相比现有的一次导数预测模型,在相同可接受误差率范围内,该模型能将预测时长拓宽至对比模型的1.6倍.同时,当预测时长拓展至2.5s时,该模型的预测准确率比对比模型高3.84%.

关键词: 多处理器片上系统(MPSoCs), RC热传导模型, 温度预测模型

Abstract:

The regional temperature prediction is the basis of the efficient heat dissipation in multiprocessor system-on-chips (MPSoCs).Based on the thermal resistance and capacitance (Thermal RC) model, this paper proposed a predictive thermal model combined with the second derivative.It predicts the temperature accurately with low complexity, and increases the prediction time length within a certain prediction error range to reduce the number of times that the prediction module is invoked and the extra power consumption.Experimental results show that, compared to the existing model combined with the first derivative, the proposed model increases the prediction length by 1.6 times within the same acceptable prediction error range.When the prediction time length is increased to 2.5s, the prediction accuracy of the proposed model is 3.84% higher than that of the contrastive model.

Key words: multiprocessor system-on-chips (MPSoCs), thermal resistance and capacitance (Thermal RC) model, predictive thermal model

中图分类号: