About this role
Summary: This internship investigates hybrid performance modeling techniques combining ML-driven insights with analytical architectural models. The role involves evaluating model transferability and design-space exploration for hardware generations using CVA6 architectures.
### Sujet de stage
The French Atomic Energy and Alternative Energies Commission (CEA) is a major player in research, development and innovation. This technological research organization is active in three main areas: energy, information and health technologies, and defense. Recognized as an expert in its fields, CEA is fully integrated into the European research area and is expanding its presence internationally. The Laboratory for Systems and Technology Integration (LIST), located in the southern Île-de-France region (Saclay), has the mission of contributing to technology transfer and promoting innovation in the field of parallel computing systems.
The internship will be conducted within the Environmental Design and Architecture Laboratory (LECA) and will contribute to the advancement of its expanding research activities in AI-driven Electronic Design Automation (EDA).
### Description de l'offre
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*
### Profil du candidat
- 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