Autoscaling of Cores in Multicore Processors using Power and Thermal Workload Signatures

Autoscaling of cloud clusters based on dynamic estimation of workloads is a well-known practice in data center management. However, this practice has not been widely adopted in the multicore processor area due to the lack of a real-time workload classification front end. In this paper, we present a novel methodology for core autoscaling in multicore processors. The methodology is based on the identification of workload signatures at both the core and the thread level. In particular, correlations between thread-based performance counters are used to decide thread migration policies to maximize per-core utilization and reduce the number of active cores. Power, thermal, and performance-aware autoscaling policies are presented, and extensive numerical experiments are used to illustrate the advantages of our algorithm for real-time multicore power and performance management.