Analyzing Thermal Variations on a Multi-core Processor

멀티코아 프로세서의 온도변화 분석

  • Lee, Sang-Jeong (Dept. of Computer Science and Eng., Soonchunhyang University) ;
  • Yew, Pen-Chung (Dept. of Computer Science and Eng., University of Minnesota, Institute of Information Science)
  • 이상정 (순천향대학교 컴퓨터학부) ;
  • Received : 2009.11.20
  • Published : 2010.11.25

Abstract

This paper studies thermal characteristics of a mix of CPU-intensive and memory-intensive application workloads on a multi-core processor. Especially, we focus on thermal variations during program execution because thermal variations are more critical than average temperatures and their ranges for thermal management. New metrics are proposed to quantify such thermal variations for a workload. We study the thermal variations using SPEC CPU2006 benchmarks with varying cooling conditions and frequencies on an Intel Core 2 Duo processor. The results show that applications have distinct thermal variations characteristics. Such variations are affected by cooling conditions,operating frequencies and multiprogramming workload. Also, there are distinct spatial thermal variations between cores. Our new metrics and their results from this study provide useful insight for future research on multi-core thermal management.

본 논문에서는 멀티코아 프로세서 상에서 프로세서와 메모리를 집중적으로 사용하는 다양한 워크로드들에 대한 온도특성을 연구한다. 일반적으로 프로세서의 온도관리를 위한 측정 지표로 평균온도와 온도범위 보다는 온도변화의 정도가 더 중요하다. 따라서 본 논문에서는 프로그램 실행 중에 온도변화를 분석하고, 워크로드의 온도변화의 정도를 정량화하는 측정 지표를 제안한다. 제안된 온도변화 측정 지표를 사용하여 인텔 Core 2 Duo 프로세서 상의 SPEC CPU2006 벤치마크들에 대해 쿨링 조건 및 클럭 주파수를 변경해 가며 온도변화를 분석한다. 분석 결과, 각 벤치마크 프로그램에 따라 서로 다른 유형의 온도 변화를 보였다. 이러한 온도변화는 쿨링 조건과 동작 클럭 주파수 및 멀티프로그래밍 워크로드에 영향을 받았다. 또한 코아들 사이의 공간적 위치에 따라서도 다른 온도 변화 특성을 보였다. 본 논문에서 제안된 온도변화 측정 지표와 연구 분석된 결과들은 향후 멀티코아 온도관리를 위한 연구에 활용하면 효과적인 온도관리가 기대된다.

Keywords

References

  1. D. Brooks and M. Martonosi, "Dynamic Thermal Management for High-Performance Microprocessors," Proc. Int'l Symp. High- Performance Computer Architecture (HPCA '01), Jan. 2001.
  2. K. Cameron, H. Pyla, and S. Varadarajan, "Tempest: A Portable Tool to Identify Hot Spots in Parallel Code," Proc. Int'l Conf. Parallel Processing (ICPP '07), Sept. 2007.
  3. P. Chaparro and J. Gonzalez, "Understanding the Thermal Implications of Multi-Core Architectures," IEEE Transactions on Parallel and Distributed Systems, vol. 18, no. 8, pp.1055-1065, Aug. 2007. https://doi.org/10.1109/TPDS.2007.1092
  4. J. Choi et.al., "Thermal-aware Task Scheduling at the System Software Level," Proc. Int'l Symp. Low Power Electronics and Design (ISLPED '07), Aug. 2007
  5. J. Donald and M. Martonosi, "Techniques for Multicore Thermal Management: Classification and New Exploration," Proc. Int'l Symp. Computer Architecture (ISCA '06), June 2006.
  6. H. Hanson et al., "Thermal Response to DVFS: Analysis with an Intel Pentium M," Proc. Int'l Symp. Low Power Electronics and Design (ISLPED '07), Aug. 2007
  7. Intel Core Duo Processor and Intel Core Solo Processor on 65nm Process Datasheet, Jan. 2007.
  8. Intel Core 2 Duo Processor and Intel Core Duo Processor with Intel E7520 Chipset Development Kit User's Manual, Jan. 2007
  9. C. Isci and M.Martonosi, "Phase Characterization for Power: Evaluating Control-Flow-Based and Event-Counter-Based Techniques," Proc. Int'l Symp. High-Performance Computer Architecture (HPCA '06), Feb. 2006.
  10. F. Martinez, J. Battilan, and J. Renau, "Power Model Validation Through Thermal Measurements," Proc. Int'l Symp. Computer Architecture (ISCA '07), June 2007.
  11. A.Naveh et al., "Power and Thermal Management in the Intel Core Duo Processor," Intel Technology Journal, vol.10, issue 2 (May 2006), pp.109-122. May, 2006.
  12. L. Peh, L. Shang, and N. Jha, "HybDTM: A Coordinated Hardware-Software Approach for Dynamic Thermal Management," IEEE Design Automation Conference, June 2006.
  13. K. Skadron et al., "Temperature-Aware Microarchitecture," Proc. Int'l. Symp. Computer Architecture (ISCA '03), June 2002.