Reducing Scheduling Cost in List Scheduling Algorithms

In list scheduling algorithm, at each scheduling step one task is scheduled to the processor on which the task achieves the earliest start time. As a result, each task is tentatively scheduled to each processor to find the destination processor. This paper presents a technique to be applied to the list scheduling algorithms which significantly reduces scheduling cost without sacrificing performance. It is proved that only two tentative task scheduling are necessary for each task to find the earliest task start time. As the consequences, the list scheduling complexity is significantly reduces from O(V log (W)+EP)to O(V(log(W) +log (P))+E), where V and E are number of tasks and edges in the task graph respectively. W is the graph width and P is the number of processors. It is demonstrated that the modified version of scheduling algorithm using the described technique yield at a significantly more cost equal or better performance compared to original version of the list scheduling algorithms.