Thermal, management for high performance computing in spaceborne applications

被引:1
|
作者
Samson, JR [1 ]
Cutting, FM [1 ]
机构
[1] Honeywell Space Syst, Clearwater, FL 33764 USA
关键词
D O I
10.1109/ITHERM.2000.866832
中图分类号
O414.1 [热力学];
学科分类号
摘要
Power is a threefold problem for mobile electronic applications - generation, dissipation, and junction temperature. Of the three, dissipation is the most limiting for spaceborne applications. Advances in high performance computing and high density packaging exacerbates the power dissipation problem and, hence, the junction temperature problem. In many space applications, particularly on smaller space vehicles, articulated space radiator systems with sealed coolant loops, pumps, etc, are neither practical nor available. Hence, the ultimate limitation is the ability to radiate heat to other sinks - primarily and ultimately to deep space. This paper considers the limitation of deep space as a heat sink for given vehicle parameters such as maximum operating temperatures, available radiating surface area, and emissivity. Different techniques of vehicle cooling are reviewed with a brief discussion of the pros and cons of each technique. Consideration of current and future material availability with better thermal and electrical conductivity is presented. Better thermal conductivity tends to isothermalize the radiating area, thereby increasing radiant heat transfer proportional to the fourth power of the absolute temperature. Increased electrical conductivity reduces power consumption and hence the need for heat dissipation. Such considerations are included in projections of self-dissipation capability per circuit board using advanced composite materials. The direct radiation approach is addressed, including a brief discussion of the conflict between the need for spacing for thermal considerations versus the desire to keep the length of signal paths as short as possible and elimination of the beneficial effects of the spacecraft and chassis shielding. A comparison of power and thermal constraints for a 10 GFLOPS onboard processing system is traded off against current and future material availability, power dissipation, radiation surface area available, and the projected performance density of candidate onboard processing architectures using COTS components.
引用
收藏
页码:247 / 254
页数:8
相关论文
共 50 条
  • [1] High performance computing systems for autonomous spaceborne missions
    Sterling, T
    Katz, DS
    Bergman, L
    INTERNATIONAL JOURNAL OF HIGH PERFORMANCE COMPUTING APPLICATIONS, 2001, 15 (03): : 282 - 296
  • [2] Virtual Machine Resource Management for High Performance Computing Applications
    Shao, Zhiyuan
    Jin, Hai
    Li, Yong
    2009 IEEE INTERNATIONAL SYMPOSIUM ON PARALLEL AND DISTRIBUTED PROCESSING WITH APPLICATIONS, PROCEEDINGS, 2009, : 137 - 144
  • [3] Thermal management materials for high-performance applications
    Luedtke, A
    ADVANCED ENGINEERING MATERIALS, 2004, 6 (03) : 142 - 144
  • [4] Adaptive Fault Management of Parallel Applications for High-Performance Computing
    Lan, Zhiling
    Li, Yawei
    IEEE TRANSACTIONS ON COMPUTERS, 2008, 57 (12) : 1647 - 1660
  • [5] Development of reworkable film in high performance thermal management applications
    Collins, AP
    Cheng, CM
    2002 INTERNATIONAL SYMPOSIUM ON MICROELECTRONICS, PROCEEDINGS, 2002, 4931 : 318 - 323
  • [6] High performance computing in biomedical applications
    Bastrakov, S.
    Meyerov, I.
    Gergel, V.
    Gonoskov, A.
    Gorshkov, A.
    Efimenko, E.
    Ivanchenko, M.
    Kirillin, M.
    Malova, A.
    Osipov, G.
    Petrov, V.
    Surmin, I.
    Vildemanov, A.
    2013 INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE, 2013, 18 : 10 - 19
  • [7] High performance computing in petroleum applications
    Ewing, Richard E.
    Qin, Guan
    Zhao, Wei
    INTERNATIONAL JOURNAL OF NUMERICAL ANALYSIS AND MODELING, 2005, 2 : 43 - 57
  • [8] High performance computing applications - Appendix A
    不详
    INTERNATIONAL JOURNAL OF HIGH PERFORMANCE COMPUTING APPLICATIONS, 2001, 15 (02): : 191 - 194
  • [9] Online Resource Management in Thermal and Energy Constrained Heterogeneous High Performance Computing
    Oxley, Mark A.
    Pasricha, Sudeep
    Maciejewski, Anthony A.
    Siegel, Howard Jay
    Burns, Patrick J.
    2016 IEEE 14TH INTL CONF ON DEPENDABLE, AUTONOMIC AND SECURE COMPUTING, 14TH INTL CONF ON PERVASIVE INTELLIGENCE AND COMPUTING, 2ND INTL CONF ON BIG DATA INTELLIGENCE AND COMPUTING AND CYBER SCIENCE AND TECHNOLOGY CONGRESS (DASC/PICOM/DATACOM/CYBERSC, 2016, : 604 - 611
  • [10] Self-Aware Thermal Management for High-Performance Computing Processors
    Bartolini, Andrea
    Diversi, Roberto
    Cesarini, Daniele
    Beneventi, Francesco
    IEEE DESIGN & TEST, 2018, 35 (05) : 28 - 35