Co-Learning Bayesian Model Fusion: Efficient performance modeling of analog and mixed-signal circuits using side information
Authors: 
Fa Wang, Manzil Zaheer, Xin Li, Jean-Olivier Plouchart, Alberto Valdes-GarciaAuthors Info & Claims
Fa Wang, Manzil Zaheer, Xin Li, Jean-Olivier Plouchart, Alberto Valdes-GarciaAuthors Info & ClaimsPages 575 - 582
Abstract
Efficient performance modeling of today's analog and mixed-signal (AMS) circuits is an important yet challenging task. In this paper, we propose a novel performance modeling algorithm that is referred to as Co-Learning Bayesian Model Fusion (CL-BMF). The key idea of CL-BMF is to take advantage of the additional information collected from simulation and/or measurement to reduce the performance modeling cost. Different from the traditional performance modeling approaches which focus on the prior information of model coefficients (i.e. the coefficient side information) only, CL-BMF takes advantage of another new form of prior knowledge: the performance side information. In particular, CL-BMF combines the coefficient side information, the performance side information and a small number of training samples through Bayesian inference based on a graphical model. Two circuit examples designed in a commercial 32nm SOI CMOS process demonstrate that CL-BMF achieves up to 5× speed-up over other state-of-the-art performance modeling techniques without surrendering any accuracy.
8. References
[1]
Semiconductor Industry Associate, International Technology Roadmap for Semiconductors, 2011.
[2]
X. Li et al., Statistical Performance Modeling and Optimization, Now Publishers, 2007.
[3]
A. Singhee et al., “Beyond low-order statistical response surfaces: latent variable regression for efficient, highly nonlinear fitting”, DAC. pp. 256–261. 2007.
[4]
A. Mitev et al., “Principle Hessian direction based parameter reduction for interconnect networks with process variation”, TCCAD, pp. 632–637_ 2007.
[5]
T. Mcf Onaghy et al., “Template-free symbolic performance modeling of analog circuits via canonical-form functions and genetic programming”, IEEE TCAD, vol. 28, no. 8, pp. 1162–1175, Aug. 2009.
[6]
X. Li et al., “Asymptotic probability extraction for nonnormal performance distributions”, IEEE TCAD, vol. 26. no. 1.00. 16–37. Jan. 2007.
[7]
F. Gong et al., “Variability-aware parametric yield estimation for analog/mixed-signal circuits: concepts, algorithms, and challenges”, IEEE D&T, vol. 31, no. 4, pp. 6–15, Jan. 2014.
[8]
H. Zhang et al., “Efficient design-specific worst-case corner extraction for integrated circuits”, DAC, 386–389. 2009.
[9]
X. Li et al., “Robust analog/RF circuit design with projection-based performance modeling”, IEEE TCAD, vol. 26, no. 1, pp. 2–15, Jan. 2007.
[10]
Y. Wang et al., “Enabling efficient analog synthesis by coupling sparse regression and polynomial optimization”, DAC, pp. 1–6, 2014.
[11]
S. Sun et al., “Indirect performance sensing for on-chip analog self-healing via Bayesian model fusion”, CICC, 2013.
[12]
S. Sun et al., “Indirect performance sensing for on-chip self-healing of analog and RF circuits”, IEEE TCAS-I, vol. 61, no. 8, pp. 2243–2252, Jul. 2014.
[13]
M. Andraud et al., “One-shot calibration of RF circuits based on non-intrusive sensors”, DAC. pp. 1–6. 2014.
[14]
J.O. Plouchart et al., “Adaptive circuit design methodology and test applied to millimeter-wave circuits”, IEEE D&T, vol. 31, no. 6, pp. 8–18, Jal. 2014.
[15]
J.O. Plouchart et al., “A 18mW, 3.3dB NF, 60GHz LNA in nm SOI CMOS technology with autonomic NF calibration”, RFIC, pp. 319–322, 2015.
[16]
V. Natarajan et al., “Yield recovery of RF transceiver systems using iterative tuning-driven power-conscious performance optimization”, IEEE D&T, vol. 32, no. 1, pp. 61–69_ Jan. 2015.
[17]
X. Li et al., “Statistical regression for efficient high-dimensional modeling of analog and mixed-signal performance variations”, DAC, pp. 38–43, 2008.
[18]
X. Li, “Finding deterministic solution from underdetermined equation: large-scale performance modeling by least angle regression”, DAC, pp. 364–369, 2009.
[19]
W. Zhang et al., “Toward efficient large-scale performance modeling of integrated circuits via multi-mode/multi-corner sparse regression”, DAC, pp. 897–902, 2010.
[20]
X. Li, “Finding deterministic solution from underdetermined equation: large-scale performance variability modeling of analog/RF circuits”, IEEE TCAD, vol. 29, no. 11, pp. 1661–1668, Nov. 2010.
[21]
X. Li et al., “Large-scale statistical performance modeling of analog and mixed-signal circuits”, CICC, 2012.
[22]
T. McConaghy, “High-dimensional statistical modeling and analysis of custom integrated circuits”, CICC, pp. 1–8, 2011.
[23]
F. Wang et al., “Bayesian model fusion: large-scale performance modeling of analog and mixed-signal circuits by reusing early-stage data”, DAC, pp. 1–6, 2013.
[24]
X. Li et al., “Efficient parametric yield estimation of analog/mixed-signal circuits via Bayesian model fusion”, ICCAD, pp. 627–634, 2012.
[25]
X. Li et al., “Bayesian model fusion: a statistical framework for efficient pre-silicon validation and post-silicon tuning of complex analog and mixed-signal circuits”, ICCAD, pp. 795–802. 2013.
[26]
C. Fang et al., “BMF-BD: Bayesian model fusion on Bernoulli distribution for efficient yield estimation of integrated circuits”, DAC, 2014.
[27]
C. Fang et al., “Efficient bit error rate estimation for highspeed link by Bayesian model fusion”, DATE, pp. 1024–1029, 2015.
[28]
Q. Huang et al., “Efficient multivariate moment estimation via Bayesian model fusion for analog and mixed-signal circuits”, DAC, 2015.
[29]
S. Yu et al., “Bayesian co-training”, NIPS, pp. 1–8, 2008.
[30]
C. Bishop, Pattern Recognition and Machine Learning, Springer, 2006.
[31]
L. Yu et al., “Remembrance of transistors past: compact model parameter extraction using bayesian inference and incomplete new measurements”, DAC, pp. 1–6, 2014.
[32]
W. Zhang et al., “Virtual probe: a statistical framework for low-cost silicon characterization of nanoscale integrated circuits”, IEEE TCAD, vol. 30, no. 12, pp. 1814–1827, Dec. 2011.
[33]
S. Boyd et al., Convex Optimization, Cambridge University Press, 2004.
Index Terms
- Co-Learning Bayesian Model Fusion: Efficient performance modeling of analog and mixed-signal circuits using side information
Index terms have been assigned to the content through auto-classification.
Recommendations
Efficient performance modeling via Dual-Prior Bayesian Model Fusion for analog and mixed-signal circuits
DAC '16: Proceedings of the 53rd Annual Design Automation ConferenceIn 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 ...
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) ...
Co-Learning Bayesian Model Fusion: Efficient Performance Modeling of Analog and Mixed-Signal Circuits Using Side Information
ICCAD '15: Proceedings of the IEEE/ACM International Conference on Computer-Aided DesignEfficient performance modeling of today's analog and mixed-signal (AMS) circuits is an important yet challenging task. In this paper, we propose a novel performance modeling algorithm that is referred to as Co-Learning Bayesian Model Fusion (CL-BMF). ...
Comments
Information & Contributors
Information
Published In
929 pages
Copyright © 2015.
Publisher
IEEE Press
Publication History
Published: 01 November 2015
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 19 Feb 2025