PhD Studentship: Using Artificial Intelligence and Learning to direct Stimuli Generation in Functional Verification: Learning-based test generation (supported by Infineon Technologies UK Ltd)

University of Bristol - Computer Science

The project:  Functional verification ensures the correct functioning of complex semiconductors. Companies invest a great deal of money and effort in functional verification for various reasons – to ensure a good user experience, to comply with regulators, to avoid the considerable costs of recalls and litigation and, in safety critical applications, to prevent the loss of life.

The two state-of-the-art approaches to functional verification are constrained-random verification and formal verification. The former is inefficient, with many simulation cycles spent exploring the same state space in much the same way; guiding the tool into the interesting corner cases present in complex systems typically requires considerable input from engineers. On the other hand, formal verification can find corner cases with little manual steering, but complexity limits mean that it can only be applied exhaustively to relatively small blocks. 

We aim to use advanced learning to direct the generation of stimuli so that the interesting corner cases on a large complex design can be reached in an automated way. In this project we intend to employ statistics-based learning techniques to help find correlations between observed coverage and stimulus. In particular, we will investigate statistical techniques capable of uncertainty propagation to predict the likelihood of given stimulus to achieve verification goals. This information is expected to help direct stimulus generation in a series of iterative cycles, each refining the information available to the learner. The programme of research includes training the test generator to stay within a set of constraints, so it produces valid stimulus; training the test generator to trigger checkers in the design; and training the test generator to achieve coverage goals. Our objective is to generate otherwise hard to find input sequences and to identify complex DUT configurations. We expect that this significantly improves the level of automation and effectiveness of test generation.

How to apply:  Please make an online application for this project at http://www.bris.ac.uk/pg-howtoapply. Please select <Computer Science> on the Programme Choice page and enter details of the studentship when prompted in the Funding and Research Details sections of the form together with the name of the supervisor, Prof Kerstin Eder.

Candidate requirements:   Open to UK/EU students

A minimum 2.1 honours degree or equivalent in Computer Science or Mathematics.

Basic skills and knowledge required: Excellent programming skills and a good understanding of computer architecture are essential.

You are able to quickly pick up new programming languages and you are willing learn how to use state-of-the-art professional EDA tools. You are a competent presenter, writer and communicator.

You seek an intellectual challenge and aim to achieve excellence in your research.

Funding: UK/EU (EU applicants who have been resident in the UK for 3 years prior to application) PhD tuition fees and a tax-free stipend at the current RCUK rate (£14,296 in 2016/17, £14,553 in 2017/18), enhanced by an additional industrial top-up subject to contracts.  EU nationals resident in the EU may also apply but will qualify only for PhD tuition fees

Contacts: Prof Kerstin Eder (Kerstin.Eder@bristol.ac.uk)

Share this PhD
     
  Share by Email   Print this job   More sharing options
We value your feedback on the quality of our adverts. If you have a comment to make about the overall quality of this advert, or its categorisation then please send us your feedback
Advert information

Type / Role:

PhD

Location(s):

South West England