Simulation and Satisfiability Guided Counter-example Triage for RTL Design Debugging

Zissis Poulos1,  Yu-Shen Yang2,  Andreas Veneris1,  Bao Le1
1University Of Toronto, 2Advanced Micro Devices, Inc


Abstract

Regression verification flows in modern integrated circuit development environments expose a plethora of counter-examples during simulation. Sorting these counter-examples today is a tedious and time-consuming process. High level design debugging aims to triage these counter-examples into groups that will be assigned to the appropriate verification and/or design engineers for detailed root cause analysis. In this work, we present an automated triage process that leverages knowledge extracted from simulation and SAT-based debugging. We introduce novel metrics that correlate counter-examples based on the likelihood of sharing the same root cause. Triage is formulated as a pattern recognition problem and solved by hierarchical clustering techniques to generate groups of related counter-examples. Experimental results demonstrate an overall accuracy of 94% for the proposed automated triage framework, which corresponds to a 40% improvement over conventional scripting methods.