Minimizing Cache Usage for Real-time Systems
Binqi Sun, Tomasz Kloda, Sergio Arribas García, Giovani Gracioli, Marco Caccamo · 2023
Cache partitioning is a technique to reduce interference among tasks accessing the shared caches. To make this technique effective, cache segments must be given to the tasks that can benefit most from having their data and instructions cached for faster execution. The existing partitioning schemes for real-time systems divide the available cache among the tasks to guarantee their schedulability which is the sole optimization criterion. However, it is also preferable, especially in systems with power constraints or mixed criticalities, to reduce the total cache usage for real-time tasks.