University of Vigo
Multicore architectures, which include several processors on a single chip, are being widely touted as a solution to thermal and power problems currently limiting single-core designs. In most proposed multicore platforms, different cores share either on- or off-chip caches. The authors propose a scheduling method for real-time systems implemented on multicore platforms that encourages certain groups of tasks to be scheduled together while ensuring real-time constraints. This paper can be applied to encourage tasks that share a common working set to be executed in parallel, which makes more effective use of shared caches.