Adaptive Task Migration Policies for Thermal Control in MPSoCs

  • David Cuesta
  • Jose Ayala
  • Jose Hidalgo
  • David Atienza
  • Andrea Acquaviva
  • Enrico Macii
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 105)


In deep submicron circuits, high temperatures have created critical issues in reliability, timing, performance, coolings costs and leakage power. Task migration techniques have been proposed to manage efficiently the thermal distribution in multi-processor systems but at the cost of important performance penalties. While traditional techniques have focused on reducing the average temperature of the chip, they have not considered the effect that temperature gradients have in system reliability. In this work, we explore the benefits of thermal-aware task migration techniques for embedded multi-processor systems. We show the implementation issues of task migration policies on next generation architectural template of distributed memory multicore systems and we discuss the programmer’s implications. Built on top of this programming model, we propose several policies that are able to reduce the average temperature of the chip and the thermal gradients with a negligible performance overhead. With our techniques, hot spots and temperature gradients are decreased up to 30% with respect to state-of-the-art thermal management approaches.


Shared Memory Multiprocessor System Interprocessor Communication Task Migration Decision Engine 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Semenov OeA (2006) Impact of self-heating effect on long-term reliability and performance degradation in CMOS circuits. IEEE Trans Device Mater Reliab 6(1):17–27CrossRefGoogle Scholar
  2. 2.
    Chaparro PeA (2007) Understanding the thermal implications of multi-core architectures. IEEE Trans Parallel Distrib Syst 18(8):1055–1065CrossRefGoogle Scholar
  3. 3.
    Carta S, Acquaviva A, Del Valle PG, Atienza D, De Micheli G, Rincon F, Benini L, Mendias JM. (2007) Multi-processor operating system emulation framework with thermal feedback for systems-on-chip. In: Proceedings of the 17th ACM GLS on VLSI, pp 311–316Google Scholar
  4. 4.
    Atienza D, Del Valle PG, Paci G, Poletti F, Benini L, Micheli GD, Mendias JM, Hermida R (2007) HW-SW emulation framework for temperature-aware design in MPSoCs. ACM Trans Des Autom Electron Syst 12(3):1–26CrossRefGoogle Scholar
  5. 5.
    Mulas F, Pittau M, Buttu M, Carta S, Acquaviva A, Benini L, Atienza D (2008) Thermal balancing policy for streaming computing on multiprocessor architectures. In: Proceedings on DATE, pp 734–739Google Scholar
  6. 6.
    Gomaa M, Powell MD, Vijaykumar TN (2004) Heat-and-run: leveraging SMT and CMP to manage power density through the operating system. SIGOPS Oper Syst Rev 38(5):260–270CrossRefGoogle Scholar
  7. 7.
    Dharmasanam S. Multiprocessing with real-time operating systems.
  8. 8.
    Jerraya AA, Tenhunen H, Wolf W (2005) Guest editors introduction: multiprocessor systems-on-chips, IEEE Computer. pp 36–40Google Scholar
  9. 9.
  10. 10.
    Poletti F, Poggiali A, Marchal P (2005) Flexible hardware/software support for message passing on a distributed shared memory architecture. In: Proceedings of DATE, pp 736–741Google Scholar
  11. 11.
    Han S-I, Baghdadi A, Bonaciu M, Chae S-I, Jerraya AA (2004) An efficient scalable and flexible data transfer architecture for multiprocessor SoC with massive distributed memory. DAC, pp 250–255Google Scholar
  12. 12.
    Loghi M, Benini L, Poncino M (2004) Analyzing power consumption of message passing primitives in a single-chip multiprocessor. In: Proceedings of DATE, 2004Google Scholar
  13. 13.
    Monchiero M, PALERMO G, Silvano C, Villa O (2006) Power/Performance hardware optimization for synchronization intensive applications in MPSoCs. In: Proceedings of DATE, 2006Google Scholar
  14. 14.
    Ruggiero M, Acquaviva A, Bertozzi D, Benini L (2005) Application-specific power-aware workload allocation for voltage scalable MPSoC platforms. ICCD05, pp 87–93Google Scholar
  15. 15.
    Kumar A, Mesman B, Corporaal H, van Meerbergen J, Yajun H (2006) Global analysis of resource arbitration for MPSoC, In: Proceedings of digital system design, 9th Euromicro conference, DSD 06Google Scholar
  16. 16.
    Ma Z, Catthoor F (2006) Scalable performance-energy trade-off exploration of embedded real-time systems on multiprocessor platforms. In: Proceedings of DATE, 2006Google Scholar
  17. 17.
    Hung W-L, Xie Y, Vijaykrishnan N, Kandemir M, Irwin MJ (2005) Thermal-aware allocation and scheduling for systems-on-a-chip design. In: Proceedings of DATE, 2005Google Scholar
  18. 18.
    Li F, Kandemir M (2005) Locality-conscious workload assignment for array-based computations in MPSOC architectures, In: Proceedings of the 42nd annual conference on design automation, pp 95–100Google Scholar
  19. 19.
    Kandemir MT, Chen G (2005) Locality-aware process scheduling for embedded MPSoCs, In: Proceedings of DATE, pp 870–875Google Scholar
  20. 20.
    Bertozzi S, Acquaviva A, Poggiali A, Bertozzi D (2006) Supporting task migration in MPSoCs: a feasibility study. In: Proceedings of design, automation and test in Europe (DATE)Google Scholar
  21. 21.
    Barak A, La’adan O, Shiloh A (1999) Scalable cluster computing with MOSIX for Linux. In: Proceedings Linux expo ’99, pp 95–100Google Scholar
  22. 22.
    Zayas E (1987) Attacking the process migration bottleneck. In: Proceedings of the eleventh ACM symposium on operating systems principles, pp 13–24Google Scholar
  23. 23.
    Milojicic D, Douglis F, Paindaveine Y, Wheeler R, Zhou S (2000) Process migration survey, ACM computing surveysGoogle Scholar
  24. 24.
    Ozturk O, Kandemir M, Son SW, Karakoy M (2006) Selective code/data migration for reducing communication energy in embedded MpSoC architectures. GLSVLSI 2006Google Scholar
  25. 25.
    Benini L, Bogliolo A, De Micheli G (2000) A survey of design techniques for system-level dynamic power management. IEEE Trans VLSI Systems 8(3):299–316CrossRefGoogle Scholar
  26. 26.
    Pouwelse JA, Langendoen K, Sips H (2001) Voltage scaling on a low-power microprocessor. Mobile computing conference (MOBICOM)Google Scholar
  27. 27.
    Kwon W, Kim T (2003) Optimal voltage allocation techniques for dynamically variable voltage processors. IEEE Trans VLSI Systems, pp 125–130, June 2003Google Scholar
  28. 28.
    Pillai P, Shin K (2001) Real-time dynamic voltage scaling for low-power embedded operating systems. ACM SIGOPS 01, pp 89–102, October 2001Google Scholar
  29. 29.
    Flautner K, Mudge TN (2002) Vertigo: Automatic performance-setting for Linux. OSDI 2002Google Scholar
  30. 30.
    ARM Intelligent Energy Manager (2005) Dynamic power control for portable devices.
  31. 31.
    Andrei A, Schmitz M, Eles P, Peng Z, Al-Hashimi BM (2004) Overhead-conscious voltage selection for dynamic and leakage energy reduction of time-constrained systems. DATE04, pp 518–523Google Scholar
  32. 32.
    Andrei A, Schmitz M, Eles P, Peng Z, Al-Hashimi BM (2004) Simultaneous communication and processor voltage scaling for dynamic and leakage energy reduction in time-constrained systems. ICCAD04, pp 362–369Google Scholar
  33. 33.
    Zhu D, Melhem R, Childers B (2003) Scheduling with dynamic voltage/speed adjustment using slack reclamation in multi-processor real-time systems. IEEE Trans Parallel Distrib Syst 14:686–700CrossRefGoogle Scholar
  34. 34.
    Ruggiero M, Acquaviva A, Bertozzi D, Benini L (2005) Application-specific power-aware workload allocation for voltage scalable MPSoC platforms. ICCD05Google Scholar
  35. 35.
    Lu Z, Hein J, Humphrey M, Stan M, Lach J, Skadron K (2002) Control theoretic dynamic frequency and voltage scaling for multimedia workloads. CASES02, pp 156–163Google Scholar
  36. 36.
    Lu Y, Benini L, De Micheli G (2002) Dynamic Frequency scaling with buffer insertion for mixed workloads. IEEE Trans Comput Aided Des Integr Circuits Syst 21(11):1284–1305MathSciNetCrossRefGoogle Scholar
  37. 37.
    Im C, Kim H, Ha S (2001) Dynamic voltage scaling technique for low-power multimedia applications using buffers. ISLPED01, pp 34–39Google Scholar
  38. 38.
    Lu Z, Lach J, Stan M (2003) Reducing Multimedia Decode Power using Feedback Control. ICCD03Google Scholar
  39. 39.
    Carta S, Alimonda A, Acquaviva A, Pisano A, Benini L (2006) A control theoretic approach to energy efficient pipelined computation in MPSoCs. To appear on transaction on embedded computing systems (TECS), 2006Google Scholar
  40. 40.
    Suen TTY, Wong JSK (1992) Efficient task migration algorithm for distributed systems. IEEE Trans Parallel Distrib Syst 3(4):488–499CrossRefGoogle Scholar
  41. 41.
    Chang HWD, Oldham WJB (1995) Dynamic task allocation models for large distributed computing systems. IEEE Trans Parallel Distrib Comput Syst 6:1301–1315CrossRefGoogle Scholar
  42. 42.
    Nollet V, Avasare P, Mignolet JY, Verkest D (2005) Low cost task migration initiation in a heterogeneous MP-SoC. In: Proceedings of the conference on DATE, pp 252–253Google Scholar
  43. 43.
    Bertozzi S, Acquaviva A, Bertozzi D, Poggiali A (2006) Supporting task migration in multi-processor systems-on-chip: a feasibility study. In: Proceedings of the conference on DATE, pp 15–20Google Scholar
  44. 44.
    Barcelos D, Brião EW, Wagner FR (2007) A hybrid memory organization to enhance task migration and dynamic task allocation in NoC-based MPSoCs. In: Proceedings of the 20th annual conference on Integrated circuits and systems design, pp 282–287Google Scholar
  45. 45.
    Brião EW, Barcelos D, Wronski F, Wagner FR (2007) Impact of task migration in NoC-based MPSoCs for soft real-time applications. In: Proceedings of the international conference on VLSI, pp 296–299Google Scholar
  46. 46.
    Pittau M, Alimonda A, Carta S, Acquaviva A (2007) Impact of task migration on streaming multimedia for embedded multiprocessors: A quantitative evaluation. In: Embedded systems for real-time multimedia, 2007. ESTIMedia 2007. IEEE/ACM/IFIP Workshop on, pp 59–64 Google Scholar
  47. 47.
    Acquaviva A, Alimonda A, Carta S, Pittau M (2008) Assessing task migration impact on embedded soft real-time streaming multimedia applications. In: EURASIP journal on embedded systems, Vol. 2008, Article ID 518904Google Scholar
  48. 48.
    Donald J, Martonosi M (2006) Techniques for multicore thermal management: Classification and new exploration. In: Proceedings of the 33rd international symposium on computer architecture, pp 78–88Google Scholar
  49. 49.
    Puschini D, Clermidy F, Benoit P, Sassatelli G, Torres L (2008) Temperature-aware distributed run-time optimization on MP-SoC using game theory. In: IEEE computer society annual symposium on VLSIGoogle Scholar
  50. 50.
    Gomaa M, Powell MD, Vijaykumar TN (2004) Heat-and-run: leveraging SMT and CMP to manage power density through the operating system. In: Proceedings of the 11th international conference on architectural support for programming languages and operating systems, pp 260–270Google Scholar
  51. 51.
    Yang J, Zhou X, Chrobak M, Zhang Y, Jin L (2008) Dynamic thermal management through task scheduling. In: Proceedings of the IEEE international symposium on performance analysis of systems and software, pp 191–201Google Scholar
  52. 52.
    Yeo I, Kim EJ (2009) Temperature-aware scheduler based on thermal behavior grouping in multicore systems. In: Proceedings of the conference on DATE 2009Google Scholar
  53. 53.
    ST Microelectronics and CEA, Platform 2012: A Many-core programmable accelerator for ultra-efficient embedded computing in nanometer technology, ST Whitepaper, 2009,
  54. 54.
    Intel, Single-Chip Cloud Computer.
  55. 55.
    Pham D, et al. (2003) The design and implementation of a first generation CELL processor. IEEE/ACM ISSCC, pp 184–186, 2005. July 2003Google Scholar
  56. 56.
    uClinux, Embedded Linux Microcontroller Project.
  57. 57.
    Friebe L, Stolberg H-J, Berekovic M, Moch S, Kulaczewski MB, Dehnhardt A, Pirsch P (2003) HiBRID-SoC: A system-on-chip architecture with two multimedia DSPs and a RISC core. IEEE international SOC conference, September 2003, pp 85–88Google Scholar
  58. 58.
    van der Wolf P, de Kock E, Henriksson T, Kruijtzer W, Essink G (2004) Design and programming of embedded multiprocessors: an interface-centric approach, CODES+ISSS, pp 206–217Google Scholar
  59. 59.
    Paci G, Marchal P, Poletti F, Benini L (2006) Exploring temperature-aware design in low-power MPSoCs. In: Proceedings of the DATE, vol 1. pp 1–6Google Scholar
  60. 60.
    Flautner K, Mudge T (2002) Vertigo: automatic performance-setting for Linux. SIGOPS Oper Syst Rev 36(SI):105–116CrossRefGoogle Scholar
  61. 61.
    Huang W, Stant MR, Sankaranarayanan K, Ribando RJ, Skadron K (2008) Many-core design from a thermal perspective. In: Proceedings of the 45th annual DAC, pp 746–749Google Scholar
  62. 62.
    Skadron K, Stan MR, Sankaranarayanan K, Huang W, Velusamy S, Tarjan D (2004) Temperature-aware microarchitecture: Modeling and implementation. ACM Trans Archit Code Optim 1(1):94–125CrossRefGoogle Scholar
  63. 63.
    Mulas F, Atienza D, Acquaviva A, Carta S, Benini L, De Micheli G (2009) Thermal balancing policy for multiprocessor stream computing platforms. IEEE transactions on computer-aided desing of integrated circuits and systems, Vol 28(12):1870–1882 Google Scholar

Copyright information

© Springer Science+Business Media B.V. 2011

Authors and Affiliations

  • David Cuesta
    • 1
  • Jose Ayala
    • 1
  • Jose Hidalgo
    • 1
  • David Atienza
    • 2
  • Andrea Acquaviva
    • 3
  • Enrico Macii
    • 3
  1. 1.Complutense UniversityMadridSpain
  2. 2.Ecole Polytechnique Fédérale de LausanneLausanneSwitzerland
  3. 3.Politecnico di TorinoTurinItaly

Personalised recommendations