ABSTRACT
In this paper, we propose a novel Dual-Prior Bayesian Model Fusion (DP-BMF) algorithm for performance modeling. Different from the previous BMF methods which use only one source of prior knowledge, DP-BMF takes advantage of multiple sources of prior knowledge to fully exploit the available information and, hence, further reduce the modeling cost. Based on a graphical model, an efficient Bayesian inference is developed to fuse two different prior models and combine the prior information with a small number of training samples to achieve high modeling accuracy. Several circuit examples demonstrate that the proposed method can achieve up to 1.83× cost reduction over the traditional one-prior BMF method without surrendering any accuracy.
- Semiconductor Industry Associate. (2011). International Technology Roadmap for Semiconductors {Online}. Available: www.iers.net/Links/2011ITRS/Home2011.htm.Google Scholar
- A. Singhee, et al., "Beyond low-order statistical response surfaces: latent variable regression for efficient, highly nonlinear fitting," IEEE DAC, pp. 256--261, 2007. Google ScholarDigital Library
- A. Mitev, et al., "Principle Hessian direction based parameter reduction for interconnect networks with process variation," IEEE ICCAD, pp. 632--637, 2007. Google ScholarDigital Library
- T. McConaghy, et al., "Template-free symbolic performance modeling of analog circuits via canonical-form functions and genetic programming," IEEE Trans. on CAD, vol. 28, no. 8, pp. 1162--1175, 2009. Google ScholarDigital Library
- X. Li, et al., "Asymptotic probability extraction for nonnormal performance distributions," IEEE Trans. on CAD, vol. 26, no. 1, pp. 16--37, 2007. Google ScholarDigital Library
- M. Sengupta, et al., "Application-specific worst case corners using response surfaces and statistical models." Computer-Aided Design of Integrated Circuits and Systems, IEEE Trans. on CAD, vol. 24, no. 9, pp. 1372--1380, 2005. Google ScholarDigital Library
- V. Natarajan, et al.,"Yield recovery of RF transceiver systems using iterative tuning-driven power-conscious performance optimization," IEEE Design & Test of Comp., vol. 32, no. 1, pp. 61--69, 2015.Google Scholar
- X. Li, "Finding deterministic solution from underdetermined equation: large-scale performance variability modeling of analog/RF circuits," IEEE Trans. on CAD, vol. 29, no. 11, pp. 1661--1668, 2010. Google ScholarDigital Library
- T. McConaghy, "High-dimensional statistical modeling and analysis of custom integrated circuits," IEEE CICC, pp. 1--8, 2011Google Scholar
- X. Li, et al., "Efficient parametric yield estimation of analog/mixed-signal circuits via Bayesian model fusion," IEEE ICCAD, pp. 627--634, 2012. Google ScholarDigital Library
- F. Wang, et al., "Bayesian model fusion: large-scale performance modeling of analog and mixed-signal circuits by reusing early-stage data," IEEE DAC, pp. 1--6, 2013. Google ScholarDigital Library
- F. Wang, et al., "Co-learning Bayesian model fusion: efficient performance modeling of analog and mixed-signal circuits using side information," IEEE ICCAD, pp. 575--582, 2015. Google ScholarDigital Library
- S. Yu, et al., "Bayesian co-training," NIPS, pp. 1--8, 2008.Google ScholarDigital Library
- C. Bishop, Pattern Recognition and Machine Learning, Springer, 2006. Google ScholarDigital Library
- Q. Huang, et al, "Efficient multivariate moment estimation via Bayesian model fusion for analog and mixed-signal circuits," IEEE DAC, pp. 169:1--169:6, 2015. Google ScholarDigital Library
Recommendations
Efficient multivariate moment estimation via Bayesian model fusion for analog and mixed-signal circuits
DAC '15: Proceedings of the 52nd Annual Design Automation ConferenceA critical-yet-challenging problem of analog/mixed-signal circuit validation in either pre-silicon or post-silicon stage is to estimate the parametric yield of the performances. In this paper, we propose a novel Bayesian model fusion method for ...
Efficient parametric yield estimation of analog/mixed-signal circuits via Bayesian model fusion
ICCAD '12: Proceedings of the International Conference on Computer-Aided DesignParametric yield estimation is one of the most critical-yet-challenging tasks for designing and verifying nanoscale analog and mixed-signal circuits. In this paper, we propose a novel Bayesian model fusion (BMF) technique for efficient parametric yield ...
Post-silicon performance modeling and tuning of analog/mixed-signal circuits via Bayesian model fusion
ICCAD '12: Proceedings of the International Conference on Computer-Aided DesignPost-silicon tuning has recently emerged as an important technique to combat large-scale uncertainties (e.g., process variation, device modeling errors, etc) for today's nanoscale circuits. This talk presents a novel Bayesian Model Fusion (BMF) ...
Comments