Causal probabilistic input dependency learning for switching model in VLSI circuits

ABSTRACT

Switching model captures the data-driven uncertainty in logic circuits in a comprehensive probabilistic framework. Switching is a critical factor that influences dynamic, active leakage power, coupling noises in CMOS implementations. In this work, we model the input-space by a causal graphical probabilistic model that encapsulates the dependencies in inputs in a compact, minimal fashion and also allows for instantiations of the vector-space that closely match the underlying dependencies, with the constraint that the reduced vector-space captures the dependencies in the larger dataset accu-rately. Results on ISCAS benchmark show that average error is limited to 1.8% while we achieve a compaction ratio of 300.

REFERENCES

• 1: Judea Pearl, Probabilistic reasoning in intelligent systems: networks of plausible inference, Morgan Kaufmann Publishers Inc., San Francisco, CA, 1988
• 2: R. Radjassamy , J. D. Carothers, Vector Compaction for Efficient Simulation-Based Power Estimation, Proceedings of the IEEE Symposium on IC/Package Design Integration, p.138, February 02-03, 1998
• 3: R. E. Neapolitan, "Learning Bayesian Networks", Prentice Hall Series in Artificial Intelligence, 2004.
• 4: J. Cheng, D. Belland W. Liu, " Learning Bayesian Networks from Data: An Efficient Approach Based on Information Theory", Technical Report, Department of Computer Science, University of Alberta, 1998.
• 5: Sanjukta Bhanja , N. Ranganathan, Swtiching activity estimation of VLSI circuits using Bayesian networks, IEEE Transactions on Very Large Scale Integration (VLSI) Systems, v.11 n.4, p.558-567, August 2003 [doi>10.1109/TVLSI.2003.816144]
• 6: Jie Cheng , David A. Bell , Weiru Liu, Learning belief networks from data: an information theory based approach, Proceedings of the sixth international conference on Information and knowledge management, p.325-331, November 10-14, 1997, Las Vegas, Nevada, United States [doi>10.1145/266714.266920]
• 7: P. Spirtes, C. Glymour, R. Scheines, "Causation, Prediction and Search", MIT Press, 2nd Edition, 2000.
• 8: Robert G. Cowell , Steffen L. Lauritzen , A. Philip David , David J. Spiegelhalter , V. Nair , J. Lawless , M. Jordan , David J. Spiegelhater, Probabilistic Networks and Expert Systems, Springer-Verlag New York, Inc., Secaucus, NJ, 1999
• 9: Chi-Ying Tsui , Radu Marculescu , Diana Marculescu , Massoud Pedram, Improving the efficiency of power simulators by input vector compaction, Proceedings of the 33rd annual conference on Design automation, p.165-168, June 03-07, 1996, Las Vegas, Nevada, United States [doi>10.1145/240518.240549]
• 10: R. Marculescu, D. Marculescu, M. Pedram, "Sequence Compaction for Power Estimation: Theory and Practice", IEEE Trans. on Computer-Aided Design of Integrated Circuits and Systems, vol.18, No.7, pp. 973--993, July 1999.
• 11: R. Marculescu, D. Marculescu, M. Pedram, "Vector Compaction Using Dynamic Markov Models", IEICE Trans. on Fundamentals, vol. E80A, No.10 pp. 1924--1933, 1997.
• 12: Alberto Macii , Enrico Macii , Massimo Poncino , Riccardo Scarsi, Stream synthesis for efficient power simulation based on spectral transforms, Proceedings of the 1998 international symposium on Low power electronics and design, p.30-35, August 10-12, 1998, Monterey, California, United States [doi>10.1145/280756.280764]
• 13: R. Marculescu, D. Marculescu, and M. Pedram, "Probabilistic Modeling of Dependencies During Switching Activity Anal-ysis", IEEE Transaction on Computer-Aided Design of Integrated Circuits and Systems, vol. 17-2, pp. 73--83, February 1998.
• 14: URL http://www.hugin.com/

INDEX TERMS

Primary Classification:
  B. Hardware
  B.8 Performance and Reliability
      B.8.2 Performance Analysis and Design Aids

General Terms:
Performance

Keywords:
Bayesian networks, cross-talk estimation, power estimation, probabilistic learning, vector compaction