Fast deployment of alternate analog test using Bayesian model fusion

In this paper, we address the problem of limited training sets for learning the regression functions in alternate analog test. Typically, a large volume of real data needs to be collected from different wafers and lots over a long period of time to be able to train the regression functions with accuracy across the whole design space and apply alternate test with high confidence. To avoid this delay and achieve a fast deployment of alternate test, we propose to use the Bayesian model fusion technique that leverages prior knowledge from simulation data and fuses this information with data from few real circuits to draw accurate regression functions across the whole design space. The technique is demonstrated for an alternate test designed for RF low noise amplifiers.

[1]  Bruno Allard,et al.  Combining Internal Probing with Artificial Neural Networks for Optimal RFIC Testing , 2006, 2006 IEEE International Test Conference.

[2]  Abhijit Chatterjee,et al.  Low-cost alternate EVM test for wireless receiver systems , 2005, 23rd IEEE VLSI Test Symposium (VTS'05).

[3]  Yiorgos Makris,et al.  Enrichment of limited training sets in machine-learning-based analog/RF test , 2009, 2009 Design, Automation & Test in Europe Conference & Exhibition.

[4]  Manuel J. Barragan Asian,et al.  Efficient selection of signatures for analog/RF alternate test , 2013, 2013 18th IEEE European Test Symposium (ETS).

[5]  A. Chatterjee,et al.  Low-cost test of embedded RF/analog/mixed-signal circuits in SOPs , 2004, IEEE Transactions on Advanced Packaging.

[6]  Chenjie Gu,et al.  Efficient moment estimation with extremely small sample size via bayesian inference for analog/mixed-signal validation , 2013, 2013 50th ACM/EDAC/IEEE Design Automation Conference (DAC).

[7]  Yiorgos Tsiatouhas,et al.  Adjustable RF Mixers' Alternate Test Efficiency Optimization by the Reduction of Test Observables , 2013, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[8]  Florence Azaïs,et al.  Making predictive analog/RF alternate test strategy independent of training set size , 2012, 2012 IEEE International Test Conference.

[9]  Abhijit Chatterjee,et al.  Alternate Test of RF Front Ends with IP Constraints: Frequency Domain Test Generation and Validation , 2006, 2006 IEEE International Test Conference.

[10]  D. Ruppert.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction , 2004 .

[11]  Yiorgos Makris,et al.  Nonlinear decision boundaries for testing analog circuits , 2005, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[12]  Abhijit Chatterjee,et al.  Analog Sensor Based Testing of Phase-Locked Loop Dynamic Performance Parameters , 2013, 2013 22nd Asian Test Symposium.

[13]  Christopher M. Bishop,et al.  Pattern Recognition and Machine Learning (Information Science and Statistics) , 2006 .

[14]  Abhijit Chatterjee,et al.  A Low-Cost Test Methodology for Dynamic Specification Testing of High-Speed Data Converters , 2007, J. Electron. Test..

[15]  Jean-Olivier Plouchart,et al.  Indirect performance sensing for on-chip analog self-healing via Bayesian model fusion , 2013, Proceedings of the IEEE 2013 Custom Integrated Circuits Conference.

[16]  Abhijit Chatterjee,et al.  Production deployment of a fast transient testing methodology for analog circuits: case study and results , 2003, International Test Conference, 2003. Proceedings. ITC 2003..

[17]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.

[18]  Abhijit Chatterjee,et al.  Dynamic Specification Testing and Diagnosis of High-Precision Sigma-Delta ADCs , 2013, IEEE Design & Test.

[19]  Salvador Mir,et al.  Adaptive Alternate Analog Test , 2011, IEEE Design & Test of Computers.

[20]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[21]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[22]  Florence Azaïs,et al.  Smart selection of indirect parameters for DC-based alternate RF IC testing , 2012, 2012 IEEE 30th VLSI Test Symposium (VTS).

[23]  Chenjie Gu,et al.  Efficient parametric yield estimation of analog/mixed-signal circuits via Bayesian model fusion , 2012, 2012 IEEE/ACM International Conference on Computer-Aided Design (ICCAD).

[24]  Abhijit Chatterjee,et al.  Concurrent RF test using optimized modulated RF stimuli , 2004, 17th International Conference on VLSI Design. Proceedings..

[25]  Abhijit Chatterjee,et al.  Prediction of analog performance parameters using fast transienttesting , 2002, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..

[26]  Rouwaida Kanj,et al.  Bayesian Model Fusion: Large-Scale Performance Modeling of Analog and Mixed-Signal Circuits by Reusing Early-Stage Data , 2016, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..

[27]  Salvador Mir,et al.  Experiences with non-intrusive sensors for RF built-in test , 2012, 2012 IEEE International Test Conference.