Abstract
This paper explores the application of symbolic regression for building models of probability distributions in which the accuracy at the distributions’ tails is critical. The problem is of importance to cutting-edge industrial integrated circuit design, such as designing SRAM memory components (bitcells, sense amps) where each component has extremely low probability of failure. A naive approach is infeasible because it would require billions of Monte Carlo circuit simulations. This paper demonstrates a flow that efficiently generates samples at the tails using importance sampling, then builds genetic programming symbolic regression models in a space that captures the tails – the normal quantile space. These symbolic density models allow the circuit designers to analyze the tradeoff between high-sigma yields and circuit performance. The flow is validated on two modern industrial problems: a bitcell circuit on a 45nm TSMC process, and a sense amp circuit on a 28nm TSMC process.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Deb, Kalyanmoy, Pratap, Amrit, Agarwal, Sameer, and Meyarivan, T. (2002). A fast and elitist multiobjective genetic algorithm: Nsga-ii. IEEE Transactions on Evolutionary Computation, 6:182–197.
Defoin Platel, Michael, Verel, Sébastien, Clergue, Manuel, and Chami, Malik (2007). Density estimation with genetic programming for inverse problem solving. In et al.,Marc Ebner, editor, Proc. European Conference on Genetic Programming, volume 4445 of Lecture Notes in Computer Science, pages 45–54. Springer.
Drennan, P. and McAndrew, C. (1999). A comprehensive mosfet mismatch model. In Proc. International Electron Devices Meeting.
Hastie, T., Tibshirani, R., and Friedman, J.H. (2001). The Elements of Statistical Learning. Springer.
Hesterberg, T.C. (1988). Advances in importance sampling. PhD thesis, Statistics Department, Stanford University.
Kanj, R., Joshi, R.V., and Nassif, S.R. (2006). Mixture importance sampling and its application to the analysis of sram designs in the presence of rare failure events. In Proc. Design Automation Conference, pages 69–72.
Koza, John R. (1992). Genetic Programming: On the Programming of Computers by Means of Natural Selection. MIT Press, Cambridge, MA, USA.
McConaghy,T. and Gielen,G.G.E. (2006).Canonical formfunctions as a simple means for genetic programming to evolve human-interpretable functions. In Proc. Genetic and Evolutionary Computation Conference, pages 855–862.
McConaghy, T. and Gielen, G.G.E. (2009). Template-free symbolic performance modeling of analog circuits via canonical form functions and genetic programming. IEEE Trans. Comput.-Aided Design of Integr. Circuits and Systems, 28(8):1162–1175.
Vladislavleva, E. (2008). Model-based Problem Solving through Symbolic Regression via Pareto Genetic Programming. PhD thesis, Tilburg University.
Whigham, P. A. (2000). Induction of a marsupial density model using genetic programming and spatial relationships. Ecological Modelling, 131(2-3):299–317.
Yao, Xin, Member, Senior, Liu, Yong, Member, Student, and Lin, Guangming (1999). Evolutionary programming made faster. IEEE Transactions on Evolutionary Computation, 3:82–102.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer Science+Business Media, LLC
About this chapter
Cite this chapter
McConaghy, T. (2011). Symbolic Density Models of One-in-a-Billion Statistical Tails via Importance Sampling and Genetic Programming. In: Riolo, R., McConaghy, T., Vladislavleva, E. (eds) Genetic Programming Theory and Practice VIII. Genetic and Evolutionary Computation, vol 8. Springer, New York, NY. https://doi.org/10.1007/978-1-4419-7747-2_10
Download citation
DOI: https://doi.org/10.1007/978-1-4419-7747-2_10
Published:
Publisher Name: Springer, New York, NY
Print ISBN: 978-1-4419-7746-5
Online ISBN: 978-1-4419-7747-2
eBook Packages: Computer ScienceComputer Science (R0)