On The Design and Application of Thermal Isolation Servers

<p>Dataset.</p> <p>Recently, there has been an increasing trend towards executing real-time applications on multi-core platforms.<br> However, this complicates the design problem, as applications running on different cores can interfere<br> due to shared resources and mediums. In this paper, we focus on thermal interference, where a given task (τ1)<br> heats the processor, resulting in reduced service (due to Dynamic Thermal Management (DTM)) to another<br> task (τ2). In real-time domain, where tasks have deadline constraints, thermal interference is a substantial<br> problem as it directly impacts the Worst Case Execution Time (WCET) of the effected application (τ2). The<br> problem exacerbates as we move to mixed-criticality systems, where the criticality of τ2 may be greater than<br> the criticality of τ1, complicating the certification process.<br> In this paper,we propose a server based strategy (Thermal Isolation Server (TI Server))which can be used to<br> avoid thermal interference of applications.We also present a heuristic to design TI Servers to meet the timing<br> constraints of all tasks and the thermal constraints of the system. TI Servers are time/space composable, and<br> can be applied to a variety of task models. We also evaluate TI Servers on a hardware test-bed for validation<br> purposes.</p>