Advertisement

Machine Learning in Alternate Testing of Integrated Circuits

  • John LiaperdosEmail author
  • Angela Arapoyanni
  • Yiorgos Tsiatouhas
Chapter
Part of the Learning and Analytics in Intelligent Systems book series (LAIS, volume 1)

Abstract

Integrated circuit (IC) fabrication involves sophisticated and sensitive equipment, while design complexity and scale of integration are increasing in order to obtain the largest functionality within the smallest possible chip area. As ICs scale down, increasing uncertainties in the manufacturing processes lead to increased numbers of malfunctioning chips that have to be detected and withdrawn early in the production stage in order to assure product quality. Testing an IC for compliance with its specifications might require a considerable amount of time and resources, since a wide range of different tests—each tailored for a specific performance characteristic—should be performed, resulting in the collection of extremely large data sets that correspond to test data. In order to reduce test time and cost, several machine learning techniques have been applied for the identification of patterns and non-linear correlations among test data and performance characteristics. Furthermore, data analytics have achieved promising results in areas such as test quality prediction and fault diagnosis. In this chapter, the Alternate Test paradigm is presented since it is probably the most well-established machine learning application in the field of IC testing. Alternate Test is performed by the exploitation of a set of common test observables—produced using simple stimuli and cost-effective equipment of low complexity—that are sufficiently correlated to all performance characteristics of interest. Following the supervised learning approach, non-linear regression models are constructed for each performance characteristic, that provide accurate performance predictions based on the values of the measured test observables. Using statistical feature selection techniques, a low dimensionality can be obtained for the set of test observables, by which a further reduction in test time and cost can be achieved.

References

  1. 1.
    E. Acar, S. Ozev, Defect-based RF testing using a new catastrophic fault model, in Proceedings of the IEEE International Test Conference (ITC) (2005), pp. 429–437Google Scholar
  2. 2.
    A. Ahmadi, M.M. Bidmeshki, A. Nahar, B. Orr, M. Pas, Y. Makris, A machine learning approach to fab-of-origin attestation, in 2016 IEEE/ACM International Conference on Computer-Aided Design (ICCAD) (2016), pp. 1–6.  https://doi.org/10.1145/2966986.2966992
  3. 3.
    S.S. Akbay, A. Halder, A. Chatterjee, D. Keezer, Low-cost test of embedded RF/analog/mixed-signal circuits in SOPs. IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst. 27(2), 352–363 (2004)CrossRefGoogle Scholar
  4. 4.
    M. Allen, Understanding Regression Analysis (Springer, US, 1997)Google Scholar
  5. 5.
    F.D. Bernardinis, M.I. Jordan, A. SangiovanniVincentelli, Support vector machines for analog circuit performance representation, in Proceedings 2003. Design Automation Conference (2003), pp. 964–969.  https://doi.org/10.1145/775832.776074
  6. 6.
    S. Bhattacharya, A. Chatterjee, Use of embedded sensors for built-in-test RF circuits., in Proceedings of International Test Conference (ITC) (2004), pp. 801–809Google Scholar
  7. 7.
    S. Bou-Sleiman, M. Ismail, Built-in-self-test and digital self-calibration for RF SoCs, in SpringerBriefs in Electrical and Computer Engineering (Springer, New York, 2011)Google Scholar
  8. 8.
    T. Das, A. Gopalan, C. Washburn, P. Mukund, Self-calibration of input-match in RF front-end circuitry. IEEE Trans. Circuits Syst. II 52(12), 821–825 (2005)CrossRefGoogle Scholar
  9. 9.
    K. Dufrene, R. Weigel, A novel IP2 calibration method for low-voltage downconversion mixers, in Proceedings of the IEEE International Symposium on Radio Frequency Integrated Circuits (RFIC), San Jose, CA, USA (2006), pp. 292–295Google Scholar
  10. 10.
    J.H. Friedman, Multivariate adaptive regression splines. Ann. Stat. 19, 1–141 (1991)MathSciNetCrossRefGoogle Scholar
  11. 11.
    E. Garcia-Moreno, K. Suenaga, R. Picos, S. Bota, M. Roca, E. Isern, Predictive test strategy for CMOS RF mixers. Integr. VLSI J. 42, 95–102 (2009)CrossRefGoogle Scholar
  12. 12.
    A. Goyal, M. Swaminathan, A. Chatterjee, A novel self-healing methodology for RF amplifier circuits based on oscillation principles, in Proceedings of the IEEE Design Automation & Test in Europe (DATE) (2009), pp. 1656–1661Google Scholar
  13. 13.
    A. Goyal, M. Swaminathan, A. Chatterjee, Self-calibrating embedded RF down-conversion mixers, in Proceedings of the IEEE Asian Test Symposium (ATS), Taichung, Taiwan (2009), pp. 249–254Google Scholar
  14. 14.
    D. Han, B.S. Kim, A. Chatterjee, DSP-driven self-tuning of RF circuits for process-induced performance variability. IEEE Trans. VLSI Syst. 18(2), 305–314 (2010)CrossRefGoogle Scholar
  15. 15.
    K. Huang, H.G. Stratigopoulos, S. Mir, Fault diagnosis of analog circuits based on machine learning, in 2010 Design, Automation Test in Europe Conference Exhibition (DATE 2010) (2010), pp. 1761–1766.  https://doi.org/10.1109/DATE.2010.5457099
  16. 16.
    R. Khereddine, L. Abdallah, E. Simeu, S. Mir, F. Cenni, Adaptive logical control of RF LNA performances for efficient energy consumption, in Proceedings of the IFIP/IEEE International Conference on Very Large Scale Integration (VLSI-SoC) (2010), pp. 518–525Google Scholar
  17. 17.
    N. Kupp, P. Drineas, M. Slamani, Y. Makris, Confidence estimation in non-RF to RF correlation-based specification test compaction, in Proceedings of the 13th European Test Symposium (ETS) (2008), pp. 35–40Google Scholar
  18. 18.
    N. Kupp, Y. Makris, Integrated optimization of semiconductor manufacturing: a machine learning approach, in 2012 IEEE International Test Conference (2012), pp. 1–10.  https://doi.org/10.1109/TEST.2012.6401531
  19. 19.
    B. Li, P.D. Franzon, Machine learning in physical design, in 2016 IEEE 25th Conference on Electrical Performance of Electronic Packaging and Systems (EPEPS) (2016), pp. 147–150.  https://doi.org/10.1109/EPEPS.2016.7835438
  20. 20.
    I. Liaperdos, L. Dermentzoglou, A. Arapoyanni, Y. Tsiatouhas, Fault detection in RF mixers combining defect-oriented and alternate test strategies, in Conference on Design of Circuits and Integrated Systems (DCIS) (2011)Google Scholar
  21. 21.
    I. Liaperdos, L. Dermentzoglou, A. Arapoyanni, Y. Tsiatouhas, A test technique and a BIST circuit to detect catastrophic faults in RF mixers, in Conference on Design and Technology of Integrated Systems in the Nanoscale Era (DTIS) (2011)Google Scholar
  22. 22.
    J. Liaperdos, A. Arapoyanni, Y. Tsiatouhas, Adjustable RF mixers’ alternate test efficiency optimization by the reduction of test observables. IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst. 32(9), 1383–1394 (2013).  https://doi.org/10.1109/TCAD.2013.2255128CrossRefGoogle Scholar
  23. 23.
    J. Liaperdos, A. Arapoyanni, Y. Tsiatouhas, A method to adjust the accuracy of analog/RF alternate tests, in Proceedings 28th Conference on Design of Circuits and Integrated Systems (DCIS) (2013)Google Scholar
  24. 24.
    J. Liaperdos, A. Arapoyanni, Y. Tsiatouhas, A test and calibration strategy for adjustable RF circuits. Analog. Integr. Circuits Signal Process. 74(1), 175–192 (2013).  https://doi.org/10.1007/s10470-012-9981-xCrossRefGoogle Scholar
  25. 25.
    J. Liaperdos, H.G. Stratigopoulos, L. Abdallah, Y. Tsiatouhas, A. Arapoyanni, X. Li, Fast deployment of alternate analog test using Bayesian model fusion, in Proceedings of Conference on Design, Automation and Test in Europe (DATE), pp. 1030–1035 (2015)Google Scholar
  26. 26.
    J. Liaperdos, A. Arapoyanni, Y. Tsiatouhas, Improved alternate test accuracy using weighted training sets, in 2016 Conference on Design of Circuits and Integrated Systems (DCIS) (2016), pp. 1–6.  https://doi.org/10.1109/DCIS.2016.7845263
  27. 27.
    J. Liaperdos, A. Arapoyanni, Y. Tsiatouhas, State reduction for efficient digital calibration of analog/RF integrated circuits. Analog. Integr. Circuits Signal Process. 90(1), 65–79 (2017).  https://doi.org/10.1007/s10470-016-0880-4CrossRefGoogle Scholar
  28. 28.
    C. Lim, Y. Xue, X. Li, R.D. Blanton, M.E. Amyeen, Diagnostic resolution improvement through learning-guided physical failure analysis, in 2016 IEEE International Test Conference (ITC) (2016), pp. 1–10.  https://doi.org/10.1109/TEST.2016.7805824
  29. 29.
    Q. Ma, Y. He, F. Zhou, A new decision tree approach of support vector machine for analog circuit fault diagnosis. Analog. Integr. Circuits Signal Process. 88(3), 455–463 (2016).  https://doi.org/10.1007/s10470-016-0775-4CrossRefGoogle Scholar
  30. 30.
    S.A. Maas, Microwave Mixers (Artech House Publishers, 1993)Google Scholar
  31. 31.
    D. Maliuk, H. Stratigopoulos, Y. Makris, Machine learning-based BIST in analog/RFICs, in Mixed-Signal Circuits, Devices, Circuits, and Systems, ed. by T. Noulis (CRC Press, 2016), pp. 266–290Google Scholar
  32. 32.
    V. Natarajan, S. Sen, S.K. Devarakond, A. Chatterjee, A holistic approach to accurate tuning of RF systems for large and small multiparameter perturbations, in Proceedings of the 28th VLSI Test Symposium (VTS) (2010), pp. 331–336Google Scholar
  33. 33.
    S.J. Park, H. Yu, M. Swaminathan, Preliminary application of machine-learning techniques for thermal-electrical parameter optimization in 3-d ic, in 2016 IEEE International Symposium on Electromagnetic Compatibility (EMC) (2016), pp. 402–405.  https://doi.org/10.1109/ISEMC.2016.7571681
  34. 34.
    S.J. Park, B. Bae, J. Kim, M. Swaminathan, Application of machine learning for optimization of 3-D integrated circuits and systems. IEEE Trans. Very Large Scale Integr. (VLSI) Syst. 25(6), 1856–1865 (2017).  https://doi.org/10.1109/TVLSI.2017.2656843CrossRefGoogle Scholar
  35. 35.
    C.W. Pui, G. Chen, Y. Ma, E.F.Y. Young, B. Yu, Clock-aware ultrascale FPGA placement with machine learning routability prediction: (invited paper), in 2017 IEEE/ACM International Conference on Computer-Aided Design (ICCAD) (2017), pp. 929–936.  https://doi.org/10.1109/ICCAD.2017.8203880
  36. 36.
    X. Ren, V.G. Tavares, R.D.S. Blanton, Detection of illegitimate access to JTAG via statistical learning in chip, in 2015 Design, Automation Test in Europe Conference Exhibition (DATE) (2015), pp. 109–114Google Scholar
  37. 37.
    S. Rodriguez, A. Rusu, L.R. Zheng, M. Ismail, Digital calibration of gain and linearity in a CMOS RF mixer, in Proceedings of the IEEE International Symposium on Circuits and Systems (ISCAS), Seattle, USA (2008), pp. 1288–1291Google Scholar
  38. 38.
    M. Sachdev, J. de Gyvez, Defect-oriented testing for nano-metric CMOS VLSI circuits, in Frontiers in Electronic Testing (Springer, 2007)Google Scholar
  39. 39.
    P. Song, Y. He, W. Cui, Statistical property feature extraction based on FRFT for fault diagnosis of analog circuits. Analog. Integr. Circuits Signal Process. 87(3), 427–436 (2016).  https://doi.org/10.1007/s10470-016-0721-5CrossRefGoogle Scholar
  40. 40.
    H.G. Stratigopoulos, S. Mir, E. Acar, S. Ozev, Defect filter for alternate RF test, in Proceedings of the IEEE European Test Symposium (2009), pp. 161–166Google Scholar
  41. 41.
    H.G. Stratigopoulos, S. Mir, Y. Makris, Enrichment of limited training sets in machine-learning-based analog/RF test, in Conference on Design, Automation and Test in Europe (DATE) (2009), pp. 1668–1673Google Scholar
  42. 42.
    K. Suenaga, R. Picos, S. Bota, M. Roca, E. Isern, E. Garcia-Moreno, Built-in test strategy for CMOS RF mixers, in Conference on Design of Circuits and Integrated Systems (DCIS) (2005)Google Scholar
  43. 43.
    H.M. Torun, M. Swaminathan, A.K. Davis, M.L.F. Bellaredj, A global Bayesian optimization algorithm and its application to integrated system design. IEEE Trans. Very Large Scale Integr. (VLSI) Syst. 26(4), 792–802 (2018).  https://doi.org/10.1109/TVLSI.2017.2784783CrossRefGoogle Scholar
  44. 44.
    P. Variyam, S. Cherubal, A. Chatterjee, Prediction of analog performance parameters using fast transient testing. IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst. 21(3), 349–361 (2002)CrossRefGoogle Scholar
  45. 45.
    A.S.S. Vasan, M.G. Pecht, Electronic circuit health estimation through kernel learning. IEEE Trans. Ind. Electron. 65(2), 1585–1594 (2018).  https://doi.org/10.1109/TIE.2017.2733419CrossRefGoogle Scholar
  46. 46.
    R. Voorakaranam, S. Cherubal, A. Chatterjee, A signature test framework for rapid production testing of RF circuits, in Proceedings of Design, Automation and Test in Europe Conference and Exhibition (DATE) (2002), pp. 186–191Google Scholar
  47. 47.
    Y. Zhu, J. Xiong, Modern big data analytics for “old-fashioned” semiconductor industry applications, in 2015 IEEE/ACM International Conference on Computer-Aided Design (ICCAD) (2015), pp. 776–780.  https://doi.org/10.1109/ICCAD.2015.7372649

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • John Liaperdos
    • 1
    Email author
  • Angela Arapoyanni
    • 2
  • Yiorgos Tsiatouhas
    • 3
  1. 1.Department of Computer EngineeringTechnological Educational Institute of PeloponneseSpartaGreece
  2. 2.Department of Informatics and TelecommunicationsNational and Kapodistrian University of AthensAthensGreece
  3. 3.Department of Computer Science and EngineeringUniversity of IoanninaIoanninaGreece

Personalised recommendations