Scalable precision cache analysis for real-time software

Abstract

Caches are needed to increase the processor performance, but the temporal behavior is difficult to predict, especially in embedded systems with preemptive scheduling. Current approaches use simplified assumptions or propose complex analysis algorithms to bound the cache-related preemption delay. In this paper, a scalable preemption delay analysis for associative instruction caches to control the analysis precision and the time-complexity is proposed. An accurate preemption delay calculation is integrated into a cache-aware schedulability analysis. The framework is evaluated in several experiments.