Adaptive test selection for post-silicon timing validation: A data mining approach

Test failure data produced during post-silicon validation contain accurate design- and process-specific information about the DUD (design-under-debug). Prior research efforts and industry practice focused on feeding this information back to the design flow via bug root-cause analysis. However, the value of this silicon data for helping further improvement of the post-silicon validation process has been largely overlooked. In this paper, we propose an adaptive test selection method to progressively tune the validation plan using knowledge automatically mined from the bug sightings during post-silicon validation. Experimental results demonstrate that the proposed fault-model-free data mining approach can prioritize those tests capable of uncovering more silicon timing errors, resulting in significant reduction of validation time and effort.

[1]  Yoav Freund,et al.  Experiments with a New Boosting Algorithm , 1996, ICML.

[2]  Magdy S. Abadir,et al.  Design-Silicon Timing Correlation A Data Mining Perspective , 2007, 2007 44th ACM/IEEE Design Automation Conference.

[3]  Irith Pomeranz,et al.  On n-detection test sets and variable n-detection test sets for transition faults , 1999, Proceedings 17th IEEE VLSI Test Symposium (Cat. No.PR00146).

[4]  Jing Wang,et al.  Scan-Based Speed-Path Debug for a Microprocessor , 2012, IEEE Design & Test of Computers.

[5]  Kwang-Ting Cheng,et al.  Timing-reasoning-based delay fault diagnosis , 2006, Proceedings of the Design Automation & Test in Europe Conference.

[6]  Alon Gluska.  Coverage-oriented verification of Banias , 2003, Proceedings 2003. Design Automation Conference (IEEE Cat. No.03CH37451).

[7]  Kwang-Ting Cheng,et al.  False-path-aware statistical timing analysis and efficient path selection for delay testing and timing validation , 2002, DAC '02.

[8]  Magdy S. Abadir,et al.  Linking Statistical Learning to Diagnosis , 2008, IEEE Design & Test of Computers.

[9]  Srikanth Venkataraman,et al.  Automated Debug of Speed Path Failures Using Functional Tests , 2009, 2009 27th IEEE VLSI Test Symposium.

[10]  Kwang-Ting Cheng,et al.  Delay testing considering power supply noise effects , 1999, International Test Conference 1999. Proceedings (IEEE Cat. No.99CH37034).

[11]  Chandramouli V. Kashyap,et al.  Silicon Speedpath Measurement and Feedback into EDA flows , 2007, 2007 44th ACM/IEEE Design Automation Conference.

[12]  J. Ross Quinlan,et al.  Induction of Decision Trees , 1986, Machine Learning.

[13]  Kwang-Ting Cheng,et al.  On error modeling of electrical bugs for post-silicon timing validation , 2012, 17th Asia and South Pacific Design Automation Conference.

[14]  Li-C. Wang,et al.  On silicon-based speed path identification , 2005, 23rd IEEE VLSI Test Symposium (VTS'05).

[15]  Miron Abramovici,et al.  In-System Silicon Validation and Debug , 2008, IEEE Design & Test of Computers.

[16]  Kwang-Ting Cheng,et al.  Delay testing considering crosstalk-induced effects , 2001, Proceedings International Test Conference 2001 (Cat. No.01CH37260).

[17]  Kwang-Ting Cheng,et al.  Post-silicon bug detection for variation induced electrical bugs , 2011, 16th Asia and South Pacific Design Automation Conference (ASP-DAC 2011).

[18]  Suriyaprakash Natarajan,et al.  Case Study on Speed Failure Causes in a Microprocessor , 2008, IEEE Design & Test of Computers.

[19]  Kwang-Ting Cheng,et al.  A case study of Time-Multiplexed Assertion Checking for post-silicon debugging , 2010, 2010 IEEE International High Level Design Validation and Test Workshop (HLDVT).