Exemplar-based Failure Triage for Regression Design Debugging

Modern regression verification often exposes myriads of failures at the pre-silicon stage. Typically, these failures need to be properly grouped into bins, which then have to be distributed to engineers for detailed analysis. The above process is coined as failure triage, and is nowadays increasing in complexity, as the size of both design logic and verification environment continues to grow. However, it remains a predominantly manual process that can prolong the debug cycle and jeopardize time-sensitive design milestones. In this paper, we propose an exemplar-based data-mining formulation of failure triage that efficiently automates both failure grouping and bin distribution. The proposed framework maps failures as data points, applies an affinity-propagation (AP) clustering algorithm, and operates in both metric and non-metric spaces, offering complete flexibility and significant user control over the process. Experimental results show that the proposed approach groups related failures together with 87 % accuracy on the average, and improves bin distribution accuracy by 21 % over existing methods.