Scheduling stochastic tasks with parallelizable contents in multiprocessor systems

In this paper, we present a new heuristic algorithm to schedule a set of independent stochastic tasks with parallelizable contents in multiprocessor systems. Each task is described by its deadline and its time cost distribution, which is given in terms of mean and variance. A scheduled task may run as one unit on a single processor or partitioned into k parallel parts running on k different processors. The proposed algorithm exploits parallelism in tasks, if it is necessary, and distributes them among the available processors to yield a high probability of meeting their deadlines and, hence obtain better schedulability