Probabilistic Design: A Survey of Probabilistic CMOS Technology and Future Directions for Terascale IC Design

  • Lakshmi N. B. Chakrapani
  • Jason George
  • Bo Marr
  • Bilge E. S. Akgul
  • Krishna V. Palem
Part of the IFIP International Federation for Information Processing book series (IFIPAICT, volume 249)

Highly scaled CMOS devices in the nanoscale regime would inevitably exhibit statistical or probabilistic behavior. Such behavior is caused by process variations, and other perturbations such as noise. Current circuit design methodologies, which depend on the existence of “deterministic” devices that behave consistently in temporal and spatial contexts do not admit considerations for probabilistic behavior. Admittedly, power or energy consumption as well as the associated heat dissipation are proving to be impediments to the continued scaling (down) of device sizes. To help overcome these challenges, we have characterized CMOS devices with probabilistic behavior (probabilistic CMOS or PCMOS devices) at several levels: from foundational principles to analytical modeling, simulation, fabrication, measurement as well as exploration of innovative approaches towards harnessing them through system-on-a-chip architectures. We have shown that such architectures can implement a wide range of probabilistic and cognitive applications. All of these architectures yield significant energy savings by trading probability with which the device operates correctly—lower the probability of correctness, the greater the energy savings. In addition to these PCMOS based innovations, we will also survey probabilistic arithmetic—a novel framework through which traditional computing units such as adders and multipliers can be deliberately designed to be erroneous, while being characterized by a well-defined probability of correctness. We demonstrate that in return for erroneous behavior, significant energy and performance gains can be realized through probabilistic arithmetic (units)—over a factor of 4.62X in the context of an FIR filter used in a H.264 video decoding—where the gains are quantified through the energy-performance product (or EPP). These gains are achieved through a systematic probabilistic design methodology enabled by a design space spanning the probability of correctness of the arithmetic units, and their associated energy savings.


Energy Saving Probability Parameter Very Large Scale Integration Full Adder Probabilistic Behavior 
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.
    B. E. S. Akgul, L. N. Chakrapani, P. Korkmaz, and K. V. Palem. Probabilistic CMOS tech-nology: A survey and future directions. In Proceedings of The IFIP International Conference on Very Large Scale Integration, 2006.Google Scholar
  2. 2.
    S. Borkar, T. Karnik, S. Narendra, J. Tschanz, A. Keshavarzi, and V. De. Parameter variations and impact on circuits and microarchitecture. In Proceedings of the 40th Design Automation Conference, pages 338-342, 2003.Google Scholar
  3. 3.
    L. N. Chakrapani, B. E. S. Akgul, S. Cheemalavagu, P. Korkmaz, K. V. Palem, and B. Se-shasayee. Ultra efficient embedded SOC architectures based on probabilistic cmos tech-nology. In Proceedings of The 9th Design Automation and Test in Europe (DATE), pages 1110-1115, Mar. 2006.Google Scholar
  4. 4.
    J. Chang and M. Pedram. Energy minimization using multiple supply voltages. In Proc. of IEEE Transactions on VLSI Systems, volume 5, pages 436 -443, Dec. 1997.CrossRefGoogle Scholar
  5. 5.
    S. Cheemalavagu, P. Korkmaz, and K. V. Palem. Ultra low-energy computing via probabilis-tic algorithms and devices: CMOS device primitives and the energy-probability relationship. In Proceedings of The 2004 International Conference on Solid State Devices and Materials, pages 402-403, Tokyo, Japan, Sept. 2004.Google Scholar
  6. 6.
    S. Cheemalavagu, P. Korkmaz, K. V. Palem, B. E. S. Akgul, and L. N. Chakrapani. A probabilistic CMOS switch and its realization by exploiting noise. In Proceedings of The IFIP International Conference on Very Large Scale Integration, 2005.Google Scholar
  7. 7.
    T. H. Cormen, C. E. Leiserson, R. L. Rivest, and C. Stein. Introduction to Algorithms, Second Edition. MIT Press and McGraw-Hill, 2001.Google Scholar
  8. 8.
    Y. Z. Ding and M. O. Rabin. Hyper-Encryption and everlasting security. In Proceedings of the 19th Annual Symposium on Theoretical Aspects of Computer Science; Lecture Notes In Computer Science, volume 2285, pages 1-26, 2002.MathSciNetGoogle Scholar
  9. 9.
    N. Ermolova and S. Haggman. Simplified bounds for the complementary error function; application to the performance evaluation of signal-processing systems. In Proceedings of the 12th European Signal Processing Conference, pages 1087-1090, Sept. 2004.Google Scholar
  10. 10.
    A. M. Ferrenberg, D. P. Landau, and Y. J. Wong. Monte carlo simulations: Hidden errors from “good” random number generators. Phys. Rev. Let, 69:3382-3384, 1992.CrossRefGoogle Scholar
  11. 11.
    H. Fuks. Non-deterministic density classifiation with diffusive probabilistic cellular au-tomata. Physical Review E, Statistical, Nonlinear, and Soft Matter Physics, 66, 2002.Google Scholar
  12. 12.
    E. Gelenbe. Random neural networks with negative and positive signals and product form solution. Neural Computation, 1(4):502-511, 1989.CrossRefGoogle Scholar
  13. 13.
    J. George, B. Marr, B. E. S. Akgul, and K. Palem. Probabilistic arithmetic and energy effi-cient embedded signal processing. In International Conference on Compilers, Architecture, and Synthesis for Embedded Systems CASES, 2006.Google Scholar
  14. 14.
    J. Hartmanis and R. E. Stearns. On the computational complexity of algorithms. Transactions of the American Mathematical Society, 117, 1965.Google Scholar
  15. 15.
    R. Hedge and N. R. Shanbhag. Soft digital signal processing. IEEE Transactions on VLSI, 9(6):813-823, Dec. 2001.CrossRefGoogle Scholar
  16. 16.
    Intel Corporation. SA-1100 microprocessor technical reference manual, Sept. 1998.Google Scholar
  17. 17.
    E. Jaynes. Probability Theory: The Logic of Science. Cambridge University Press, Cambridge, UK, 2003.MATHGoogle Scholar
  18. 18.
    L. B. Kish. End of Moore’s law: thermal (noise) death of integration in micro and nano electronics. Physics Letters A, 305:144-149, 2002.CrossRefGoogle Scholar
  19. 19.
    P. Korkmaz, B. E. S. Akgul, L. N. Chakrapani, and K. V. Palem. Advocating noise as an agent for ultra low-energy computing: Probabilistic CMOS devices and their characteristics. Japanese Journal of Applied Physics (JJAP), 45(4B):3307-3316, Apr. 2006.CrossRefGoogle Scholar
  20. 20.
    M. Lu. Arithmetic and Logic in Computer Systems. John Wiley & Sons, Inc., Hoboken, NJ, 2004.CrossRefGoogle Scholar
  21. 21.
    D. MacKay. Bayesian interpolation. Neural Computation, 4(3), 1992.Google Scholar
  22. 22.
    A. Manzak and C. Chaktrabarti. Variable voltage task scheduling algorithms for minimiz-ing energy/power. In Proc. of IEEE Transactions on Very Large Scale Integration (VLSI) Systems, volume 11, pages 270-276, Apr. 2003.CrossRefGoogle Scholar
  23. 23.
    D. Marpe, T. Wiegand, and G. J. Sullivan. The H.264/MPEG4-AVC standard and its fidelity range extensions. IEEE Communications Magazine, Sept. 2005.Google Scholar
  24. 24.
    J. D. Meindl and J. A. Davis. The fundamental limit on binary switching energy for terascale integration (TSI). IEEE; Journal of Solid State Circuits, 35:1515-1516, Oct. 2000.CrossRefGoogle Scholar
  25. 25.
    K. Natori and N. Sano. Scaling limit of digital circuits due to thermal noise. Journal of Applied Physics, 83:5019-5024, 1998.CrossRefGoogle Scholar
  26. 26.
    K. V. Palem. Proof as experiment: Probabilistic algorithms from a thermodynamic perspec- tive. In Proceedings of The International Symposium on Verification (Theory and Practice), Taormina, Sicily, June 2003.Google Scholar
  27. 27.
    K. V. Palem. Energy aware computing through probabilistic switching: A study of limits. IEEE Transactions on Computers, 54(9):1123-1137, 2005.CrossRefGoogle Scholar
  28. 28.
    K. V. Palem, B. E. S. Akgul, and J. George. Variable scaling for computing elements. Inven- tion Disclosure, Feb. 2006.Google Scholar
  29. 29.
    M. O. Rabin. Probabilistic algorithms. In J. F. Traub, editor, Algorithms and Complexity, New Directions and Recent Trends, pages 29-39. 1976.Google Scholar
  30. 30.
    M. O. Rabin. Complexity of computations. Communications of the ACM, 20(9):625-633, 1977.MATHCrossRefMathSciNetGoogle Scholar
  31. 31.
    Random Number Generation and Testing.
  32. 32.
    N. Sano. Increasing importance of electronic thermal noise in sub-0.1mm Si-MOSFETs. The IEICE Transactions on Electronics, E83-C:1203-1211, 2000.Google Scholar
  33. 33.
    B. Shim, S. R. Sridhara, and N. R. Shanbhag. Reliable low-power digital signal process-ing via reduced precision redundancy. In Proc. of IEEE Transactions on Very Large Scale Integration (VLSI) Systems, volume 12, pages 497-510, May 2004.CrossRefGoogle Scholar
  34. 34.
    R. Solovay and V. Strassen. A fast monte-carlo test for primality. SIAM Journal on Comput- ing, 1977.Google Scholar
  35. 35.
    L. Wang and N. R. Shanbhag. Low-power filtering via adaptive error-cancellation. IEEE Transactions on Signal Processing, 51:575-583, Feb. 2003.CrossRefGoogle Scholar
  36. 36.
    Y. Yeh and S. Kuo. An optimization-based low-power voltage scaling technique using mul-tiple supply voltages. In Proc. of IEEE Internaitonal Symposium on ISCAS 2001, volume 5, pages 535 - 538, May 2001.Google Scholar
  37. 37.
    Y. Yeh, S. Kuo, and J. Jou. Converter-free multiple-voltage scaling techniques for low-power cmos digital design. In Proc. of IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, volume 20, pages 172-176, Jan. 2001.CrossRefGoogle Scholar

Copyright information

© International Federation for Information Processin 2008

Authors and Affiliations

  • Lakshmi N. B. Chakrapani
    • 1
  • Jason George
    • 1
  • Bo Marr
    • 1
  • Bilge E. S. Akgul
    • 1
  • Krishna V. Palem
    • 1
  1. 1.School of Electrical and Computer EngineeringGeorgia Institute of TechnologyAtlantaUSA

Personalised recommendations