Lower-bound complexity and high performance mechanism for scheduling dependent-tasks on heterogeneous grids

List-scheduling caught the spotlights in solving the problem of task scheduling due to its simplicity, low time complexity and high performance. In general, most list-scheduling algorithms consist of two main phases, task prioritization phase and grid-nodes assignment phase. Performance of both phases has a direct influence on the overall algorithm performance. The performance of grid-nodes assignment mechanism may be enhanced using duplication-based heuristics that may lead to an increase in the mechanism complexity. Mainly three lower-bound complexity grid-nodes assignment mechanisms are presented in the literature. These mechanisms are non-insertion based, insertion based and reverse duplicator. This paper presents a lower-bound complexity grid-nodes assignment mechanism that works with any task prioritization mechanism. Random generated application graphs in addition to real world application graphs have been used to evaluate the performance of the proposed mechanism in terms of SLR, efficiency and quality of schedules. Based on the simulation results, the proposed mechanism outperforms the other three mechanisms.