Internship Combining Analytical And Ml Models For Efficient Hw Performance Prediction - Saclay H/F - CEA

Le CEA est un acteur majeur de la recherche, au service des citoyens, de l'économie et de l'Etat.


Il apporte des solutions concrètes à leurs besoins dans quatre domaines principaux : transition énergétique, transition numérique, technologies pour la médecine du futur, défense et sécurité sur un socle de recherche fondamentale. Le CEA s'engage depuis plus de 75 ans au service de la souveraineté scientifique, technologique et industrielle de la France et de l'Europe pour un présent et un avenir mieux maîtrisés et plus sûrs.


Implanté au coeur des territoires équipés de très grandes infrastructures de recherche, le CEA dispose d'un large éventail de partenaires académiques et industriels en France, en Europe et à l'international.


Les 20 000 collaboratrices et collaborateurs du CEA partagent trois valeurs fondamentales :


- La conscience des responsabilités

- La coopération

- La curiosité

As an intern at the CEA, you will have the opportunity to work within a world-renowned research environment. Our teams consist of passionate and dedicated experts, providing an ideal setting for learning and collaboration. You will have access to state-of-the-art equipment and top-tier research resources to carry out your assignments. The work conducted may potentially lead to a scientific publication.

Context

The goal of this internship is to investigate hybrid performance modeling techniques that combine ML-based data-driven models with structured top-down analytical models.

What do we expect from you?

Using the CVA6, CVA6S, CVA6S+ architectural evolution as a case study, the internship will explore:

• Hybrid modeling: Combining simulation ML-driven performance insights with analytical architectural models.
• Transferability: Evaluating whether models developed for one hardware generation can be adapted to subsequent generations with limited retraining or recalibration.
• Design-space exploration: Assessing the ability of hybrid models to efficiently predict the impact of architectural modifications.

The internship aims to develop and evaluate a hybrid modeling methodology that balances accuracy, expressiveness, and transferability across hardware generations. The ultimate objective is to assess its potential for enabling flexible hardware design-space exploration, reducing reliance on costly cycle-accurate simulations.

References

[ISCA'25] Concorde: Fast and Accurate CPU Performance Modeling with Compositional Analytical-ML Fusion

[ICCAD'23] PANDA: Architecture-Level Power Evaluation by Unifying Analytical and Machine Learning Solutions

#Cea-List

• Required level: Master's degree or Engineering diploma
• Required Skills: Familiarity with AI, knowledge of computer architecture, proficiency in Python and C/C++, and experience with Git
• Other Qualities: Collaborative mindset and a genuine curiosity