Analysis of cache usability on modern real-time systems

Abstract

Cache memories are used in the microprocessors to close the speed gap between the processor and the main memory. Caches can minimize the memory access time by keeping a copy of the highly demanded data closer to the processor. As a result, the overall program execution time is reduced. In safety-critical real-time systems, a worst-case analysis is required, and therefore the cache memories play an essential role in the estimation of the application's worst-case execution time. A simulation tool for the cache structure was developed to provide estimated measurements for both cache predictability and the worst-case memory access time based on the used architectural model. This may help to draw some conclusions about the actual cache operation. The simulation supports several modern uni-core and multi-core architectures, including some used in real-time systems. It also allows configuring different cache structures and hierarchies. The cache architecture, configuration and memory accesses from a simulated running application are specified by the user via an input file. The simulation provides a list of traces for every access. The cache predictability can be formulated as hit and miss rates. At the same time, the traces can be used to estimate total memory access time.