Scheduling directed acyclic task graphs with coarse granularity onto multiprocessors

Abstract

The multiprocessor scheduling is the problem of mapping the tasks of a directed acyclic graph (DAG) onto the processors of a multiprocessor system in a way that minimizes the completion time. Since this problem is known to be NP-complete, many heuristic scheduling algorithms are developed to achieve near optimal schedules in a reasonable amount of computation time. In this paper we present a heuristic scheduling algorithm based on linear clustering scheme and effectiveness of proposed algorithm is assured by computer simulations.