System-level power and timing variability characterization to Compute Thermal Guarantees

With ever-increasing power densities, temperature management using software and hardware techniques has become a necessity in the design of modern electronic systems. Such techniques have to be validated and optimized with respect to the thermal guarantee they provide, i.e., a safe upper-bound on the peak temperature of the system under all operating conditions. The computation of such a guarantee depends on the power and timing characteristics of the system. In this paper, we present formalisms to capture such characteristics at the system-level and provide an analytical technique to compute a provably safe upper-bound on the peak temperature. The proposed characterization and analysis is general in that it considers an impulse-response-based thermal model, task-dependent power consumption, tasks with dynamic arrival patterns and variable resource demand, and a scheduling policy expressed as a hierarchical composition of several commonly used policies.