A distributed and self-calibrating model-predictive controller for energy and thermal management of high-performance multicores

Abstract

High-end multicore processors are characterized by high power density with significant spatial and temporal variability. This leads to power and temperature hot-spots, which may cause non-uniform ageing and accelerated chip failure. These critical issues can be tackled on-line by closed-loop thermal and reliability management policies. Model predictive controllers (MPC) outperform classic feedback controllers since they are capable of minimizing a cost function while enforcing safe working temperature. Unfortunately basic MPC controllers rely on a-priori knowledge of multicore thermal model and their complexity exponentially grows with the number of controlled cores. In this paper we present a scalable, fully-distributed, energy-aware thermal management solution. The model-predictive controller complexity is drastically reduced by splitting it in a set of simpler interacting controllers, each allocated to a core in the system. Locally, each node selects the optimal frequency to meet temperature constraints while minimizing the performance penalty and system energy. Global optimality is achieved by letting controllers exchange a limited amount of information at run-time on a neighbourhood basis. We address model uncertainty by supporting learning of the thermal model with a novel distributed self-calibration approach that matches well the controller architecture.