Low-complexity algorithms for static cache locking in multitasking hard real-time systems

Cache memories have been extensively used to bridge the gap between high speed processors and relatively slow main memories. However, they are a source of predictability problems because of their dynamic and adaptive behavior and thus need special attention to be used in hard-real time systems. A lot of progress has been achieved in the last ten years to statically predict the worst-case behavior of applications with respect to caches in order to determine safe and precise bounds on task worst-case execution times (WCETs) and cache-related preemption delays. An alternative approach to cope with caches in real-time systems is to statically lock their contents such that memory access times and cache-related preemption times are predictable. In this paper, we propose two low-complexity algorithms for selecting the contents of statically-locked caches. We evaluate their performances and compare them with those of a state of the art static cache analysis method.