Encyclopedia of Parallel Computing

2011 Edition
| Editors: David Padua

Power Wall

  • Pradip Bose
Reference work entry
DOI: https://doi.org/10.1007/978-0-387-09766-4_499

Definition

The “Power Wall” refers to the difficulty of scaling the performance of computing chips and systems at historical levels, because of fundamental constraints imposed by affordable power delivery and dissipation. The single biggest factor that has led the industry into encountering this wall in the past decade is the significant change in traditional CMOS chip design evolution, which were driven previously by Dennard scaling rules [515].

Discussion

Introduction

Power delivery and dissipation limits have emerged as a key constraint in the design of microprocessors and associated systems even for those targeted for the high end server product space. At the low end of the performance spectrum, power has always dominated over performance as the primary design constraint. However, while battery life expectancies have shown modest increases, the larger demand for increased functionality and speed has increased the severity of the power constraint in the world of handheld and...

This is a preview of subscription content, log in to check access.

Bibliography

  1. 1.
    Agrawal A, Mukhopadhyay S, Raychowdhury A, Roy K, Kim CH (2006) Leakage power analysis and reduction in nanoscale circuits. IEEE Micro 26(2):68–80Google Scholar
  2. 2.
    Albonesi D (1998) Dynamic IPC/clock rate optimization. In: Proceedings of the 25th annual international symposium on computer architecture (ISCA), ACM/IEEE Computer Society, Barcelona, pp 282–292Google Scholar
  3. 3.
    Albonesi DH, Balasubramonian R, Dropsho SG, Dwarkadas S, Friedman EG, Huang MC, Kursun V, Magklis G, Scott ML, Semeraro G, Bose P, Buyuktosunoglu A, Cook PW, Schuster SE (2003) Dynamically tuning processor resources with adaptive processing. IEEE Comput 36(12):49–58, Special Issue on Power-Aware ComputingGoogle Scholar
  4. 4.
    Barroso L, Holzle U (2007) The case for energy proportional computing. IEEE Comput 40(12):33–37Google Scholar
  5. 5.
    Bohr M (2007) A 30 year retrospective on dennard’s MOSFET scaling paper. P Solid St Circ Soc 12(1):11–13Google Scholar
  6. 6.
    Borkar S (1999) Design challenges of technology scaling. P IEEE Micro 19(4):23–29Google Scholar
  7. 7.
    Bose P, Kim S, O’Connell FP (1999) Ciarfella WA Bounds modeling and compiler optimizations for superscalar performance tuning. J Syst Architect 45:1111–1137; ElsevierGoogle Scholar
  8. 8.
    Brews JR (1979) Subthreshold behavior of uniformly and non-uniformly doped long-channel MOSFET. IEEE T Electron Dev 26:1282–1291Google Scholar
  9. 9.
    Brooks D, Bose P, Srinivasan V, Gschwind MK, Emma PG, Rosenfield MG (2003) New methodology for early-stage, microarchitecture-level power-performance analysis of microprocessors. IBM J Res Dev 47(5/6):653–662Google Scholar
  10. 10.
    Brooks D, Martonosi M (1999) Dynamically exploiting narrow width operands to improve processor power and performance. In: Proceedings of the 5th international symposium on high-performance computer architecture (HPCA-5), IEEE Computer Society, OrlandoGoogle Scholar
  11. 11.
    Brooks D, Martonosi M (2001) Dynamic thermal management for high-performance microprocessors. In: Proceedings of the 7th internatinal symposium On high performance computer architecture, IEEE Computer Society, Nuevo Leone, pp 20–24Google Scholar
  12. 12.
    Brooks DM, Bose P, Schuster SE, Jacobson H, Kudva PN, Buyuktosunoglu A, Wellman J-D, Zyuban V, Gupta M, Cook PW (2000) Power-aware microarchitecture: design and modeling challenges for next-generation microprocessors. P IEEE Micro 20(6):26–44Google Scholar
  13. 13.
    Buyuktosunoglu A et al (2000) An adaptive issue queue for reduced power at high performance. In: Proceedings ISCA Workshop on complexity-effective design (WCED), VancouverGoogle Scholar
  14. 14.
    Cruz J-L, Gonzalez A, Valero M, Topham NP (2000) Multiple-banked register file architectures. In: Proceedings of the international symposium on computer architecture (ISCA), Vancouver, pp 316–325Google Scholar
  15. 15.
    Dennard R et al (1974) Design of ion-implanted MOSFETs with very small physical dimensions. IEEE J Solid St Circ SC-9(5):256–268Google Scholar
  16. 16.
    Diefendorff K (1999) POWER4 focuses on memory bandwidth. Microprocessor Report 13(13):11–17Google Scholar
  17. 17.
    Dubey PK, Flynn MJ (1990) Optimal pipelining. J Parallel Distr Com 8(1):10–19Google Scholar
  18. 18.
    Flautner K, Kim NS, Martin S, Blaauw D, Mudge T (2002) Drowsy Caches: simple techniques for reducing leakage power. In: Proceedings of the international symposium on computer architecture (ISCA), IEEE Computer Society, AnchorageGoogle Scholar
  19. 19.
    Flynn MJ, Hung P, Rudd K (1999) Deep-submicron microprocessor design issues. P IEEE Micro 19(4):11–22Google Scholar
  20. 20.
    Gara A et al (2005) Overview of the blue gene/L system architecture. IBM J Res Dev 49(2/3):195–212Google Scholar
  21. 21.
    Gonzalez R, Horowitz M (1996) Energy dissipation in general purpose microprocessors. IEEE J Solid-St Circ 31(9):1277–1284Google Scholar
  22. 22.
    Grunwald D, Klauser A, Manne S, Pleszkun, A (1998) Confidence estimation for speculation control. In: Proceedings 25th annual international symposium on computer architecture (ISCA), ACM/IEEE Computer Society, Barcelona, pp 122–131Google Scholar
  23. 23.
    Gunther SH, Binns F, Carmean DM, Hall JC (2000) Managing the impact of increasing microprocessor power consumption. In: Proceedings of the Intel Technology JournalGoogle Scholar
  24. 24.
    Hartstein A, Puzak TR (2002) The optimum pipeline depth for a microprocessor. Proceedings of the 29th international symposium on computer architecture (ISCA-29), IEEE Computer Society, AnchorageGoogle Scholar
  25. 25.
  26. 26.
    Hu C (1996) Device and technology impact on low power electronics. In: Rabaey J (ed) Low power design methodologies. Kluwer, Boston, pp 21–35Google Scholar
  27. 27.
    Hu Z, Buyuktosunoglu A, Srinivasan V, Zyuban V, Jacobson H, Bose P (2004) Microarchitectural techniques for power gating of execution units. In: Proceedings of the international symposium on low power electronics and design (ISLPED), ACM, Newport BeachGoogle Scholar
  28. 28.
    ISSCC (International Solid State Circuits Conference) (2010) Trends Report, http://isscc.org/doc/2010/ISSCC2010∖_TechTrends.pdf
  29. 29.
    Iyer A, Marculescu D (2002) Power-performance evaluation of globally asynchronous, locally synchronous processors. In: Proceedings of the international symposium on computer architecture (ISCA), IEEE Computer Society, AnchorageGoogle Scholar
  30. 30.
    Jacobson H, Bose P, Hu Z, Eickemeyer R, Eisen L, Griswell J (2005) Stretching the limits of clock-gating efficiency in server-class processors. In: Proceedngs of the international symposium on high performance computer architecture (HPCA), IEEE Computer Society, San FranciscoGoogle Scholar
  31. 31.
    Jacobson HM (2004) Improved clock-gating through transparent pipelining. In: Proceedings of the international symposium on low Power electronics and design (ISLPED), ACM, CaliforniaGoogle Scholar
  32. 32.
    Jacobson HM et al (2002) Synchronous interlocked pipelines. In: Proceedings of the international symposium on advanced research in asynchronous circuits and systems, IEEE Computer Society, ManchesterGoogle Scholar
  33. 33.
    Kahle JA et al (2005) Introduction to the Cell multiprocessor. IBM J Res Dev 49(4/5):589–604Google Scholar
  34. 34.
    Kalla R, Sinharoy B, Starke WJ, Floyd MJ (2010) Power7: IBM’s next generation server processor. IEEE Micro 30(2):7–15Google Scholar
  35. 35.
    Kalla R, Sinharoy B, Tendler J (2004) IBM POWER5 chip: a dual-core multithreaded processor, IEEE Micro 24(2):40–47Google Scholar
  36. 36.
    Kanda K et al (2001) Design impact of positive temperature dependence on drain current in sub-1-V CMOS VLSIs. IEEE JSSC, 36(10):1559–1564Google Scholar
  37. 37.
    Karkhanis T, Bose P, Smith J (2002) Saving energy with just in time instruction delivery. In: Proceedings of the intenational symposium on low power electronics and design (ISLPED), ACM, MontereyGoogle Scholar
  38. 38.
    Kaxiras S, Hu Z, Martonosi M (2001) Cache Decay: exploiting generational behavior to reduce cache leakage power. In: Proceedings of the international symposium on computer architecture (ISCA), GoteborgGoogle Scholar
  39. 39.
    Kogge PM (1981) The architecture of pipelined computers. Hemisphere Publishing Corporation, New YorkzbMATHGoogle Scholar
  40. 40.
    Kongetira P (2004) A 32-way multithreaded SPARC® processor. Presented at Hot ChipsGoogle Scholar
  41. 41.
    Kumar R, Tullsen D, Jouppi N, Ranganathan P (2005) Heterogeneous chip multiprocessors. IEEE Comput 38(11):32–38Google Scholar
  42. 42.
    Larson AG (1973) Cost-effective processor design with an application to fast fourier transform computers. Digital systems laboratory report SU-SEL-73-037, Stanford University, Stanford; see also, Larson and Davidson (1973) Cost-effective design of special purpse processors: a fast fourier transform case study. In: Proceedings 11th annual allerton conference on circuits and system theory. University of Illinois, Champaihn-Urbana, pp 547–557Google Scholar
  43. 43.
    Leverich J, Monchiero M, Talwar V, Ranganathan P, Kozyrakis C (2009) Power management of datacenter workloads using per-core power gating. IEEE Comput Archit Lett 8(2): 48–51Google Scholar
  44. 44.
    Lungu A, Bose P, Buyuktosunoglu A, Sorin D (2009) Dynamic power gating with quality guarantees. In: Proceedings of the international symposium on low power electronics and design (ISLPED), ACM, New YorkGoogle Scholar
  45. 45.
    Madan NS, Buyuktosunoglu A, Bose P, Annavaram M (2011) Guarded power gating in a multi-core setting, presented at ISCA workshop on energy-efficient design (WEED), June 2010; to appear as a Lecture notes on computer science (LNCS) volume in 2010; see also full paper in Proceedings of the 17th international Symposium on high performance computer architecture (HPCA)Google Scholar
  46. 46.
    Manne S, Klauser A, Grunwald D (1998) Pipeline gating: speculation control for energy reduction. In: Proceedings of the 25th annual international symposium on computer architecture (ISCA), ACM/IEEE Computer Society, Barcelona, pp 132–141Google Scholar
  47. 47.
    Maro R, Bai Y, Bahar RI (2000) Dynamically reconfiguring processor resources to reduce power consumption in high-performance processors. In: Proceedings of power aware computer systems (PACS) Workshop, held in conjunction with ASPLOS, CambridgeGoogle Scholar
  48. 48.
    McNairy C, Bhatia R (2005) Montecito: a dual-core, dual-thread Itanium Processor. IEEE Micro 25(2):10–20 (see also, Hot Chips 2004)Google Scholar
  49. 49.
    Oklobdzija VG (1998) Architectural tradeoffs for low power. In: Proceedings of the ISCA Workshop on Power-Driven Microarchitectures, BarcelonaGoogle Scholar
  50. 50.
    Reed P et al (1997) 250 MHz 5 W RISC microprocessor with on-chip L2 cache controller. Dig Tech Pap IEEE Int Solid St Circ Conf 40:412Google Scholar
  51. 51.
    Sakurai T, Newton R (1990) Alpha-power law MOSFET model and its applications to CMOS inverter delay and other formulas. IEEE JSSC 25(2):584–594Google Scholar
  52. 52.
    Sanchez H et al (1997) Thermal management system for high performance PowerPC microprocessors. In: Digest of papers, IEEE COMPCON, p 325Google Scholar
  53. 53.
    Seng JS, Tullsen DM, Cai G (2000) The power efficiency of multithreaded architectures. In: Invited talk presented at: ISCA Workshop on Complexity-Effective Design (WCED), VancouverGoogle Scholar
  54. 54.
    Singhal R (2008) Inside intel core microarchitecture (Nehalem). Presented at Hot Chips-20, StanfordGoogle Scholar
  55. 55.
    Sohi G, Breach SE, Vijaykumar TN (1995) Multiscalar Processors. In: Proceedings of the 22nd annual international symposium on computer architecture, IEEE CS Press, Los Alamitos, pp 414–425Google Scholar
  56. 56.
    Srinivasan V, Brooks D, Gschwind M, Bose P, Zyuban V, Strenski PN, Emma PG (2002) Optimizing pipelines for power and performance. In: Proceedings of the 35th annual IEEE/ACM symposium on microarchitecture (MICRO-35), ACM/IEEE, IstanbulGoogle Scholar
  57. 57.
    Talks presented at the ISCA workshops on complexity effective design (WCED-2000 through WCED-2006), http://www.csl.cornell.edu/∼albonesi/wced.html
  58. 58.
    Talks presented at the kool chips workshops (1998) http://www.cs.colorado.edu/∼grunwald/LowPowerWorkshop
  59. 59.
    Talks presented at the power aware computer systems (PACS) Workshops; e.g. the 2004 offering: http://www.ece.cmu.edu/∼pacs04/
  60. 60.
    Tendler JM, Dodson JS, Fields JS Jr, Le H, Sinharoy B (2002) POWER4 system microarchitecture. IBM J Res Dev 46:(1):1–116Google Scholar
  61. 61.
    The International Technology Roadmap for Semiconductors. http://www.itrs.net/reports.html
  62. 62.
    Theme issue (1997) The future of processors. IEEE Comput 30(9):97–93Google Scholar
  63. 63.
    Tiwari V et al (1998) Reducing power in high-performance microprocessors. In: Proceedings of the IEEE/ACM Design Automation Conference. ACM, New York, pp 732–737Google Scholar
  64. 64.
    Tullsen DM, Eggers SJ, Levy HM (1995) Simultaneous Multithreading: Maximizing On-Chip parallelism. In: Proceedings of the 22nd annual internatonal symposium on computer architecture, Santa Margherita Ligure, pp 292–403Google Scholar
  65. 65.
    Yen D (2005) Chip multithreading processors enable reliable high throughput computing. Keynote speech at international symposium on reliability physics (IRPS)Google Scholar
  66. 66.
    Zyuban V (2000) Inherently lower-power high performance super scalar architectures. PhD thesis, Department of Computer Science and Engineering, University of Notre DameGoogle Scholar
  67. 67.
    Papers in the special issue of IBM Journal of Research and Development, March/May 2002Google Scholar
  68. 68.
    Zyuban V, Brooks D, Srinivasan V, Gschwind M, Bose P, Strenski P, Emma P (2004) Integrated analysis of power and performance for pipelined microprocessors. IEEE T Comput 53(8):1004–1016Google Scholar
  69. 69.
    Zyuban V, Kogge P (2000) Optimization of high-performance superscalar architectures for energy efficiency. In: Proceedings of the IEEE symposium on low power electronics and design, ACM, New YorkGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2011

Authors and Affiliations

  • Pradip Bose
    • 1
  1. 1.Reliability & Power-Aware MicroarchitecturesIBM Corp. T.J. Watson Research CenterYorktown HeightsUSA