Thermal-aware power budgeting for dark silicon chips

This invited paper summarizes two new steps towards dealing with dark silicon issues: Thermal Safe Power (TSP) and MatEx (both available as open-source tools at http://ces.itec.kit.edu/download). TSP is a novel thermal-aware power budgeting technique, which is namely an abstraction that provides safe power constraints as a function of the number of active cores. TSP conceptually and radically changes the typical design that uses a single and constant value as power budget, e.g., the Thermal Design Power (TDP). Executing cores at power values below TSP results in a higher system performance than state-of-the-art solutions, while the chip's temperature remains below the critical levels. Furthermore, runtime decisions (task migration, power gating, DVFS, etc.) are typically used to optimize resource usages. Such decisions change the power consumption, which can result in transient temperatures much higher than steady-state scenarios. To be thermally safe, it is important to evaluate the transient peaks before making resource management decisions. Hence, we developed a lightweight method for computing these transient peaks, called MatEx, based on analytically solving the system of thermal differential equations using matrix exponentials and linear algebra, instead of using regular numerical methods. TSP alleviates the pessimistic dark silicon estimations of TDP, and it enables new avenues for performance improvements. MatEx allows for lightweight transient and peak temperature computations, useful to quickly predict a chip's thermal behavior and make runtime decisions.