Machine learning-based volume diagnosis

In this paper, a novel diagnosis method is proposed. The proposed technique uses machine learning techniques instead of traditional cause-effect and/or effect-cause analysis. The proposed technique has several advantages over traditional diagnosis methods, especially for volume diagnosis. In the proposed method, since the time consuming diagnosis process is reduced to merely evaluating several decision functions, run time complexity is much lower than traditional diagnosis methods. The proposed technique can provide not only high resolution diagnosis but also statistical data by classifying defective chips according to locations of their defects. Even with highly compressed output responses, the proposed diagnosis technique can correctly locate defect locations for most defective chips. The proposed technique correctly located defects for more than 90 % (86 %) defective chips at 50× (100×) output compaction. Run time for diagnosing a single simulated defect chip was only tens of milli-seconds.

[1]  Wu-Tung Cheng,et al.  Signature Based Diagnosis for Logic BIST , 2006, 2006 IEEE International Test Conference.

[2]  Janusz Rajski,et al.  Analyzing Volume Diagnosis Results with Statistical Learning for Yield Improvement , 2007, 12th IEEE European Test Symposium (ETS'07).

[3]  Leendert M. Huisman,et al.  Diagnosing combinational logic designs using the single location at-a-time (SLAT) paradigm , 2001, Proceedings International Test Conference 2001 (Cat. No.01CH37260).

[4]  Nilanjan Mukherjee,et al.  X-Press Compactor for 1000x Reduction of Test Data , 2006, 2006 IEEE International Test Conference.

[5]  Wu-Tung Cheng,et al.  Compression mode diagnosis enables high volume monitoring diagnosis flow , 2005, IEEE International Conference on Test, 2005..

[6]  Janusz Rajski,et al.  Diagnosis of Scan Cells in BIST Environment , 1999, IEEE Trans. Computers.

[7]  Saman Adham,et al.  Scan-based BIST fault diagnosis , 1999, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..

[8]  Chien-Mo James Li,et al.  Column Parity Row Selection (CPRS) BIST Diagnosis Technique: Modeling and Analysis , 2007, IEEE Transactions on Computers.

[9]  Krishnendu Chakrabarty,et al.  Identification of error-capturing scan cells in scan-BIST with applications to system-on-chip , 2004, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[10]  Janusz Rajski,et al.  A Rapid Yield Learning Flow Based on Production Integrated Layout-Aware Diagnosis , 2006, 2006 IEEE International Test Conference.

[11]  Sujit Dey,et al.  Software-based diagnosis for processors , 2002, DAC '02.

[12]  Sudhakar M. Reddy,et al.  Convolutional compaction of test responses , 2003, International Test Conference, 2003. Proceedings. ITC 2003..

[13]  Subhasish Mitra,et al.  X-compact: an efficient response compaction technique for test cost reduction , 2002, Proceedings. International Test Conference.

[14]  Giovanni Squillero,et al.  An Effective Technique for Minimizing the Cost of Processor Software-Based Diagnosis in SoCs , 2006, Proceedings of the Design Automation & Test in Europe Conference.

[15]  Alexander J. Smola,et al.  Support Vector Method for Function Approximation, Regression Estimation and Signal Processing , 1996, NIPS.