Online Hard Real-Time Scheduling for Hypercube Multiprocessors

Scheduling sporadic tasks is a formidable problem in hard real-time systems, particularly multiprocessor systems. Until now little research has addressed this problem for hypercube multiprocessors. In this paper we study two online scheduling algorithms-Buddy/RT and Stacking, for hard real-time environments which provide guarantees at the time of arrival of a task. Buddy/RT is a straightforward extension of the well-known Buddy strategy to the real-time environment, while Stacking is a more sophisticated algorithm based on the lessons learned from Buddy/RT. The underlying concept behind the Stacking algorithm is to reduce fragmentation by`stacking' equal-sized jobs in the time dimension. The performance of the two algorithms is compared through simulation studies. We nd that the Stacking algorithm performs signiicantly better than Buddy/RT over a wide range of workloads, with no increase in complexity.