Fast Statistical Analysis Using Machine Learning

  • Rouwaida KanjEmail author
  • Rajiv V. Joshi
  • Lama Shaer
  • Ali Chehab
  • Maria Malik


In this chapter, we describe a fast statistical yield analysis methodology for memory design. At the heart of its engine is a mixture importance sampling-based methodology which comprises a uniform sampling stage and an importance sampling stage. Logistic regression-based machine learning techniques are employed for modeling the circuit response and speeding up the importance sample points simulations. To avoid overfitting, we rely on a cross-validation-based regularization framework for ordered feature selection. The methodology is comprehensive and computationally efficient. We demonstrate the methodology on an industrial state-of-the-art 14 nm FinFET SRAM design with write-assist circuitry. The results corroborate well with hardware and with the fully circuit-simulation-based approach.



The authors would like to thank the Maroun Semaan Faculty of Engineering and Architecture at the American University of Beirut for supporting Ph.D. student Miss Lama Shaer.


  1. 1.
    X. Li, H. Liu, Statistical regression for efficient high-dimensional modeling of analog and mixed-signal performance variations, in Design Automation Conference, 2008. DAC 2008. 45th ACM/IEEE (IEEE, New York, 2008), pp. 38–43Google Scholar
  2. 2.
    K. Agarwal, S, Nassif, Statistical analysis of SRAM cell stability, in Proceedings of the 43rd annual Design Automation Conference (ACM, New York, 2006), pp. 57–62Google Scholar
  3. 3.
    S. Mukhopadhyay, H. Mahmoodi, K. Roy, Statistical design and optimization of SRAM cell for yield enhancement, in Proceedings of the 2004 IEEE/ACM International Conference on Computer-Aided Design (IEEE Computer Society, Washington, DC, 2004), pp. 10–13Google Scholar
  4. 4.
    A. Singhee, R.A. Rutenbar, Statistical blockade: a novel method for very fast Monte Carlo simulation of rare circuit events, and its application, in Design, Automation, and Test in Europe (Springer, New York, 2008), pp. 235–251Google Scholar
  5. 5.
    R. Kanj, R. Joshi, S. Nassif, Mixture importance sampling and its application to the analysis of SRAM designs in the presence of rare failure events, in Design Automation Conference, 2006 43rd ACM/IEEE (IEEE, New York, 2006), pp. 69–72Google Scholar
  6. 6.
    R. Kanj, T. Li, R. Joshi, K. Agarwal, A. Sadigh, D. Winston, S. Nassif, Accelerated statistical simulation via on-demand Hermite spline interpolations, in Proceedings of the International Conference on Computer-Aided Design (IEEE Press, New York, 2011), pp. 353–360Google Scholar
  7. 7.
    M. Malik, R.V. Joshi, R. Kanj, S. Sun, H. Homayoun, T. Li, Sparse regression driven mixture importance sampling for memory design, in IEEE Transactions on Very Large Scale Integration (VLSI) Systems (2017)Google Scholar
  8. 8.
    L. Shaer, R. Kanj, R. Joshi, M. Malik, A. Chehab, Regularized logistic regression for fast importance sampling based SRAM yield analysis, in 2017 18th International Symposium on Quality Electronic Design (ISQED) (IEEE, New York, 2017), pp. 119–124Google Scholar
  9. 9.
    G.E.P. Box, J. Stuart Hunter, W. Gordon Hunter, Statistics for Experimenters: Design, Innovation, and Discovery, vol. 2 (Wiley, New York, 2005)zbMATHGoogle Scholar
  10. 10.
    J.F. Ramaley, Buffon’s noodle problem. Am. Math. Mon. 76(8), 916–918 (1969)MathSciNetCrossRefGoogle Scholar
  11. 11.
    N. Metropolis, S. Ulam, The Monte Carlo method. J. Am. Stat. Assoc. 44(247), 335–341 (1949)CrossRefGoogle Scholar
  12. 12.
    C.P. Robert. Monte Carlo Methods (Wiley Online Library, 2004)Google Scholar
  13. 13.
    T.C. Hesterberg, Advances in importance sampling, PhD Thesis, 1988Google Scholar
  14. 14.
    D.W Hosmer Jr., S. Lemeshow, R.X. Sturdivant, Applied Logistic Regression, vol. 398 (Wiley, New York, 2013)Google Scholar
  15. 15.
    A. Mojsilovic, A logistic regression model for small sample classification problems with hidden variables and non-linear relationships: an application in business analytics, in IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005. Proceedings (ICASSP’05), vol. 5 (IEEE, New York, 2005), pp. v–329Google Scholar
  16. 16.
    S. Ahmad, N.M. Ramli, H. Midi, Outlier detection in logistic regression and its application in medical data analysis, in 2012 IEEE Colloquium on Humanities, Science and Engineering (CHUSER) (IEEE, New York, 2012), pp. 503–507Google Scholar
  17. 17.
    R.S. Collica, A logistic regression yield model for SRAM bit fail patterns, in The IEEE International Workshop on Defect and Fault Tolerance in VLSI Systems, 1993 (IEEE, New York, 1993), pp. 127–135Google Scholar
  18. 18.
    X. Li, H. Liu, Statistical regression for efficient high-dimensional modeling of analog and mixed-signal performance variations, in Design Automation Conference, 2008. DAC 2008. 45th ACM/IEEE (IEEE, New York, 2008), pp. 38–43Google Scholar
  19. 19.
    A. Ng, Cs229 lecture notes (2017). Retrieved from
  20. 20.
    X. Li, Finding deterministic solution from underdetermined equation: large-scale performance variability modeling of analog/RF circuits. IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 29(11), 1661–1668 (2010)CrossRefGoogle Scholar
  21. 21.
    D. Böhning, Multinomial logistic regression algorithm. Ann. Inst. Stat. Math. 44(1), 197–200 (1992)CrossRefGoogle Scholar
  22. 22.
    D.T, Larose, Data Mining Methods & Models (Wiley, New York, 2006)Google Scholar
  23. 23.
    T.P. Minka, A comparison of numerical optimizers for logistic regression, Unpublished draft (2003)Google Scholar
  24. 24.
    S.-I. Lee, H. Lee, P. Abbeel, A.Y. Ng, Efficient L1 regularized logistic regression, in AAAI, vol. 6 (2006), pp. 401–408Google Scholar
  25. 25.
    S. Perkins, J. Theiler, Online feature selection using grafting, in Proceedings of the 20th International Conference on Machine Learning (ICML-03) (2003), pp. 592–599Google Scholar
  26. 26.
    R. Kohavi et al., A study of cross-validation and bootstrap for accuracy estimation and model selection. in Proceedings of International Joint Conference on Artificial Intelligence, IJCAI, Stanford, CA, vol. 14 (1995), pp. 1137–1145Google Scholar
  27. 27.
    R.V. Joshi, M. Ziegler, H. Wetter, C. Wandel, H, Ainspan, 14nm finfet based supply voltage boosting techniques for extreme low v min operation, in 2015 Symposium on VLSI Circuits (VLSI Circuits) (IEEE, Piscataway, 2015), pp. C268–C269CrossRefGoogle Scholar
  28. 28.
    R.V. Joshi, M.M. Ziegler, Programmable supply boosting techniques for near threshold and wide operating voltage SRAM, in 2017 IEEE Custom Integrated Circuits Conference (CICC) (IEEE, Piscataway, 2017), pp. 1–4Google Scholar
  29. 29.
    R. Joshi, R. Kanj, S. Nassif, D. Plass, Y. Chan et al., Statistical exploration of the dual supply voltage space of a 65nm PD/SOI CMOS SRAM cell, in Proceeding of the 36th European Solid-State Device Research Conference, 2006. ESSDERC 2006 (IEEE, Piscataway, 2006), pp. 315–318Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Rouwaida Kanj
    • 1
    Email author
  • Rajiv V. Joshi
    • 2
  • Lama Shaer
    • 1
  • Ali Chehab
    • 1
  • Maria Malik
    • 3
  1. 1.Maroun Semaan Faculty of Engineering and ArchitectureAmerican University of BeirutBeirutLebanon
  2. 2.IBM TJ Watson LabsYorktown HeightsUSA
  3. 3.George Mason UniversityFairfaxUSA

Personalised recommendations