Exploring the Generalizability of ML-driven Model Generation for HW Design H/F

Job description: This internship aims to develop a methodology for constructing machine learning (ML)-based models that effectively generalize across the design space of the CVA6 processor. The objective is to predict performance, power, and area (PPA) metrics based on hardware configurations while reducing the number of required simulations. One aspect of the internship involves conducting a comprehensive state-of-the-art (SoA) review of advanced ML techniques, including Generative Adversarial Networks (GANs) for data augmentation, active learning for efficient simulation selection, and regression models for predictive analysis. The intern will: Conduct a state-of-the-art review to evaluate existing ML techniques for configuration-aware modeling. Define and simulate, using an internal framework, a representative subset of CVA6 configurations to generate PPA metrics. Explore and prototype ML approaches, such as GANs, active learning, and regression models. Train and validate the models to ensure effective generalization across unseen configurations. Propose a scalable and reproducible methodology for hardware configuration-aware modeling. If time allows, the intern may also explore using the developed model for architectural exploration to efficiently identify optimized configurations.

Your profile: Required Level: Master's degree or Engineering diploma Duration: 6 months Skills Required: Familiarity with AI, knowledge of Computer Architecture, proficiency in Python and C/C++, and experience with Git Other Qualities: Strong command of English, collaborative mindset, and a genuine curiosity Application Materials: Please submit a CV together with academic transcripts and a cover letter In line with CEA's commitment to integrating people with disabilities, this job is open to all.