ABSTRACT
Non-uniform utilization of functional units in combination with hardware mechanisms such as clock gating leads to different power consumptions in different parts of a processor chip. This in turn leads to non-uniform temperature distributions and problematic local hotspots, depending on the characteristics of the currently running task. The operating system's scheduler, responsible for deciding which task to run at what time, can influence temperature distribution. Our work investigates what the operating system can do to alleviate the problem of hotspots. We propose task activity vectors describing which functional units a task uses to what degree. With the knowledge provided by these vectors, the scheduler can schedule tasks using different units successively, distribute tasks using a particular unit excessively over the system's processors, or mix tasks using different units on a SMT processor. We implemented several vector-based scheduling strategies for Linux. Our evaluations show that vector-based scheduling considerably reduces hotspots.
- F. Bellosa, A. Weissel, M. Waitz, and S. Kellner. Event-driven energy accounting for dynamic thermal management. In Proceedings of the Workshop on Compilers and Operating Systems for Low Power (COLP'03), Sept 2003.Google Scholar
- J. Choi, C.-Y. Cher, H. Franke, H. Hamann, A. Weger, and P. Bose. Thermal-aware task scheduling at the system software level. In Proceedings of the 2007 International Symposium on Low-Power Electronics and Design (ISLPED'07), Aug. 2007. Google Scholar
Digital Library
- J. Donald and M. Martonosi. Leveraging simultaneous multithreading for adaptive thermal control. In Second Workshop on Temperature-Aware Computer Systems (TACS'05), Madison, USA, June 2005.Google Scholar
- J. Donald and M. Martonosi. Techniques for multicore thermal management: Classification and new exploration SIGARCH Comput. Archit. News, 34(2):78--88, 2006. Google Scholar
Digital Library
- M. Gomaa, M. D. Powell, and T. N. Vijaykumar. Heat-and-run: leveraging SMT and CMP to manage power density through the operating system. SIGARCH Comput. Archit. News, 32(5):260--270, 2004. Google Scholar
Digital Library
- S. H. Gunther, F. Binns, D. M. Carmean, and J. C. Hall. Managing the impact of increasing microprocessor power consumption. Intel Technology Journal, 2001. Q1 issue.Google Scholar
- Y. Han, I. Koren, and C. M. Krishna. Temptor: A lightweight runtime temperature monitoring tool using performance counters. In Proceedings of the Third Workshop on Temperature-Aware Computer Systems (TACS'06), June 2006.Google Scholar
- S. Heo, K. Barr, and K. Asanovi. Reducing power density through activity migration. In Proceedings of the International Symposium on Low Power Electronics and Design (ISPLED'03), 2003. Google Scholar
Digital Library
- W. Huang, M. R. Stan, K. Skadron, K. Sankaranarayanan, S. Ghosh, and S. Velusamy. Compact thermal modeling for temperature aware design. In Proceedings of the 41st Design Automation Conference (DAC'04), 2004. Google Scholar
Digital Library
- Intel. Intel® Pentium® 4 Processor with 512-KB L2 Cache on 0.13 Micron Process Thermal Design Guidelines Design Guide, Nov. 2002.Google Scholar
- C. Isci and M. Martonosi. Runtime power monitoring in high-end processors: Methodology and empirical data. In Proceedings of the 36th Annual IEEE/ACM International Symposium on Microarchitecture (MIRCO'03), pages 93--104, Washington, DC, USA, 2003. IEEE Computer Society. Google Scholar
Digital Library
- M. T. Jones. Inside the linux scheduler. IBM Developer Works, 2006.Google Scholar
- K.-J. Lee and K. Skadron. Using performance counters for runtime temperature sensing in high-performance processors. In Proceedings of the 19th IEEE International Parallel and Distributed Processing Symposium (IPDPS'05) - Workshop 11, Apr. 2005. Google Scholar
Digital Library
- A. Merkel and F. Bellosa. Balancing power consumption in multiprocessor systems. In First ACM SIGOPS EuroSys Conference, Leuven, Belgium, Apr. 18--21 2006. Google Scholar
Digital Library
- P. Michaud and Y. Sazeides. Scheduling issues on thermally-constrained processors. Technical report, Institut de Recherche en Informatique et Systemes Aleatoires, Oct 2006.Google Scholar
- E. Rothem, J. Hermerding, C. Aviad, and C. Harel. Temperature measurement in the intel core duo processor. In Proceedings of the Twelfth International Workshop on Thermal Investigations of ICs (THERMINIC'06), Aug. 2006.Google Scholar
- K. Skadron, M. R. Stan, W. Huang, S. Velusamy, K. Sankaranarayanan, and D. Tarjan. Temperature-aware microarchitecture. In Proceedings of the 30th International Symposium on Computer Architecture (ISCA'03), June 2003. Google Scholar
Digital Library
- A. Snavely and D. M. Tullsen. Symbiotic jobscheduling for a simultaneous mutlithreading processor. SIGPLAN Not., 35(11):234--244, 2000. Google Scholar
Digital Library
- L.-T. Yeh and R. C. Chu. Thermal Management of Microelectronic Equipment. American Society of Mechanical Engineers, 2001.Google Scholar
Index Terms
Task activity vectors: a new metric for temperature-aware scheduling
Recommendations
Task activity vectors: a new metric for temperature-aware scheduling
EuroSys '08Non-uniform utilization of functional units in combination with hardware mechanisms such as clock gating leads to different power consumptions in different parts of a processor chip. This in turn leads to non-uniform temperature distributions and ...
Balancing power consumption in multiprocessor systems
EuroSys '06: Proceedings of the 1st ACM SIGOPS/EuroSys European Conference on Computer Systems 2006Actions usually taken to prevent processors from overheating, such as decreasing the frequency or stopping the execution flow, also degrade performance. Multiprocessor systems, however, offer the possibility of moving the task that caused a CPU to ...
Task Allocation and Migration Algorithm for Temperature-Constrained Real-Time Multi-Core Systems
GREENCOM-CPSCOM '10: Proceedings of the 2010 IEEE/ACM Int'l Conference on Green Computing and Communications & Int'l Conference on Cyber, Physical and Social ComputingTemperature rise will affect the stability and performance of multi-core processors. A temperature-aware task scheduling algorithm for real-time multi-core systems, called LTEDF (Low Thermal Early Deadline First), is proposed in this paper. In LTEDF, a ...







Comments