Curiosity driven AI helps find hardware interference in multi core systems
Application of curiosity driven exploration methods for hardware interference identification
Artificial Intelligence
Summary
Multi-core computer chips can have parts that slow each other down, which makes it hard to know exactly how long tasks will take—important in fields like aviation where timing is critical. The authors looked at this problem as exploring all the ways parts might interfere with each other. They used curiosity-driven AI methods, which are designed to explore new behaviors efficiently, to better find these interference patterns. Their approach covered more possible behaviors compared to simply testing randomly generated programs. This helps in understanding hardware effects more thoroughly within limited time and resources.
multi-core processorembedded systemshardware interferenceexecution timetemporal requirementscuriosity-driven explorationartificial intelligencemicro-architecturesimulationpseudo-random program generation
Authors
Ludovic Matar, Clement Moulin-Frier, Pierre-Yves Oudeyer
Abstract
The transition from single-core to multi-core architectures in safety-critical embedded systems introduces significant challenges due to inter-core interference caused by contention for shared hardware resources. Such interference affects execution times and complicates the verification of strict temporal requirements, particularly in domains such as avionics where standards require comprehensive identification of interference sources. Existing interference analysis approaches, whether manual or model-based, struggle to capture the full range of behaviors arising from the complex interactions among micro-architectural components. In this paper, we frame multi-core interference analysis as the exploration of a complex system behavior space. We propose the use of curiosity-driven exploration algorithms from artificial intelligence to systematically and efficiently cover the space of possible interference behaviors. Using a simulator-based environment, we show that the proposed approach achieves broader and more uniform behavioral coverage within a limited experimental budget compared to traditional pseudo-random program generation methods.