Considering Quality-of-Service for Resource Reduction using OpenMP

Not caring about resources means wasting them. Current task-based parallel models such as Cilk or OpenMP care only about execution performance regardless of the actual application resource needs; this can lead to over-consumption resulting in resource waste.We present a technique to overcome the resource un-awareness by extending the programming model and run-time system to dynamically adapt the allocated resources to reect the expected Quality-of-Service of the application. We show that by considering tasks' timing constraints and the expected quality-of-service in terms of real-time behavior, one can reduce the number of resources and temperature compared to a greedy work-stealing scheduler. Our implementation uses a feedback controller that continuously samples the application-experienced service and dynamically adjusts the number of resources to match the quality required by the application.QC 20140616