Machine learning-based anomaly detection for post-silicon bug diagnosis

Authors:
Andrew DeOrio;Qingkun Li;Matthew Burgess;Valeria Bertacco
Affiliations:
University of Michigan, Ann Arbor, MI;University of Michigan, Ann Arbor, MI;University of Michigan, Ann Arbor, MI;University of Michigan, Ann Arbor, MI
Venue:
Proceedings of the Conference on Design, Automation and Test in Europe
Year:
2013

Citing 8
Cited 0

An IEEE 1149.1 Based Logic/Signature Analyzer in a Chip

Proceedings of the IEEE International Test Conference on Test: Faster, Better, Sooner
The Manic Depression of Microprocessor Debug

ITC '02 Proceedings of the 2002 IEEE International Test Conference
Cooperative bug isolation

Cooperative bug isolation
A reconfigurable design-for-debug infrastructure for SoCs

Proceedings of the 43rd annual Design Automation Conference
Anomaly detection: A survey

ACM Computing Surveys (CSUR)
Increasing the efficiency of simulation-based functional verification through unsupervised support vector analysis

IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
BLoG: post-silicon bug localization in processors using bug localization graphs

Proceedings of the 47th Design Automation Conference
Post-silicon bug diagnosis with inconsistent executions

Proceedings of the International Conference on Computer-Aided Design

Quantified Score

Hi-index	0.00

Visualization

Abstract

The exponentially growing complexity of modern processors intensifies verification challenges. Traditional pre-silicon verification covers less and less of the design space, resulting in increasing post-silicon validation effort. A critical challenge is the manual debugging of intermittent failures on prototype chips, where multiple executions of a same test do not yield a consistent outcome. We leverage the power of machine learning to support automatic diagnosis of these difficult, inconsistent bugs. During post-silicon validation, lightweight hardware logs a compact measurement of observed signal activity over multiple executions of a same test: some may pass, some may fail. Our novel algorithm applies anomaly detection techniques similar to those used to detect credit card fraud to identify the approximate cycle of a bug's occurrence and a set of candidate root-cause signals. Compared against other state-of-the-art solutions in this space, our new approach can locate the time of a bug's occurrence with nearly 4x better accuracy when applied to the complex OpenSPARC T2 design.