Modeling Cache Coherence to Expose Interference

To facilitate programming, most multi-core processors feature automated mechanisms maintaining coherence between each core’s cache. These mechanisms introduce interference, that is, delays caused by concurrent access to a shared resource. This type of interference is hard to predict, leading to the mechanisms being shunned by real-time system designers, at the cost of potential benefits in both running time and system complexity. We believe that formal methods can provide the means to ensure that the effects of this interference are properly exposed and mitigated. Consequently, this paper proposes a nascent framework relying on timed automata to model and analyze the interference caused by cache coherence. 2012 ACM Subject Classification Computer systems organization → Multicore architectures; Computer systems organization → Real-time systems