Runtime resource management for lifetime extension in multi-core systems

The availability of numerous, possibly heterogeneous, processing resources in multi-core systems allows one to exploit them to optimize performance and/or power/energy consumption. In particular, strategies have been defined to map and schedule tasks on the system resources, with the aim of optimizing the adopted figure of merit, at design time, if the working context is known in advance and relatively stable, at run time when facing changing/unpredictable working conditions. However, it is important to be aware that such strategies may have an impact on the overall lifetime of the system because of aging and wear-out mechanisms. Therefore such management strategies, generally adopted for handling performance and power consumption aspects, should be enhanced in order to consider such issues. Furthermore, specific Dynamic Reliability Management (DRM) policies have been devised to deal with lifetime issues in multi-core systems, acting mainly on the workload distribution (and eventually on architectural knobs, such as voltage/frequency scaling) to mitigate the stress caused by the running applications. Here we will focus on DRM strategies, whose goal is pursuing the improvement of lifetime reliability by means of load distribution policies that identify the resource where to map a new application entering the system, or where to periodically migrate tasks to balance stress. More precisely, a selection of state-of-the-art solutions will be presented and analysed, with respect to the achieved expected lifetime, evaluated when considering the first failure as well as the sequence of failures leading to the system being unable to fulfill the user's performance of service requirements.