Using augmented BDI models for intelligent stimuli generation

Lead Research Organisation: University of Bristol
Department Name: Computer Science

Abstract

Constrained random verification (CRV) and formal verification are currently the state-of-the-art approaches to functional verification. CRV's advantage is that does not suffer from size restrictions. Hence it can be applied to large designs. However, CRV is inefficient, with many simulation cycles spent exploring the same state space. Furthermore, guiding the tools into interesting corner cases typically requires considerable manual effort from verification engineers. Conversely, formal verification can find corner cases with little manual steering; but due to complexity limits, it can only be applied exhaustively to relatively small designs. This research aims to employ BDI (Belief-Desire-Intention) intelligence, augmented by machine learning techniques, to investigate the middle ground between CRV and formal verification. A BDI-based approach offers high-level, goal-directed planning with backtracking to achieve set goals. Augmenting a BDI model with a reward/punishment system can facilitate intelligent, agent-based generation of test stimuli which can automatically find and hit the interesting corner cases on a complex design, such as a CPU. This results in less reliance on hand-written constraints and random test generation. The solution would also be applicable to other verification use-cases such as post-silicon debug and test case automation at cluster level.

Publications

10 25 50

Studentship Projects

Project Reference Relationship Related To Start End Student Name
EP/N509619/1 01/10/2016 30/09/2021
1953873 Studentship EP/N509619/1 01/11/2017 30/04/2021 Nyasha Masamba
 
Description Implemented a tree search based model (rather than a BDI model) for intelligent stimuli generation, augmented by a variety of machine learning techniques. This model was chosen because it brings together the classical planning capabilities of BDI models and it also has a dynamic learning element as more data about the stimuli is encountered.
Exploitation Route The approach could be used to accelerate the speed of digital design verification projects in the semiconductor industry. Broadly speaking, it also has the potential to reduce the industry's utilisation of resources such as compute power and human labour; these are currently utilised intensively.
Sectors Digital/Communication/Information Technologies (including Software)