A resource-centric Application Classification Approach

In this paper we present a resource-centric application classification approach that monitors data flow along the path from main memory to the cores to locate spots of high resource utilization and potential resource contention. We designate three application classes, i.e. streaming applications, last-level cache sensitive applications and applications that restrict their activity either within the cores or in the private levels of the memory hierarchy. Our classification scheme can form the basis for a number of preliminary prediction models that are capable of predicting application interference with high accuracy.