Practical multiprocessor scheduling algorithms for efficient parallel processing

Abstract

This paper describes practical optimization/approximation algorithms for scheduling a set of partially ordered computational tasks with different processing times onto a multiprocessor system so that the schedule length is minimized. Since this problem belongs to the class of “strong” NP hard problems, we must eliminate the possibility of constructing not only pseudopolynomial time optimization algorithms, but also fully polynomial time approximation schemes unless P = NP. This paper proposes a heuristic algorithm CP/MISF (Critical Path/Most Immediate Successors First) and an optimization/approximation algorithm DF/IHS (Depth First/ Implicit Heuristic Search). DF/IHS is an excellent scheduling method which can reduce markedly the space complexity and average computation time by combining the branch‐and‐bound method with CP/MISF; it allows us to solve very large‐scale problems with a few hundred tasks.

The scheduling policy on agent software evolution

“…Scheduling is arranging the order of each task execution that has been assigned. At present, task allocation and scheduling problem is NP recognized [1].…”

Multi-heuristic dynamic task allocation using genetic algorithms in a heterogeneous distributed system

“…Many heuristic algorithms exist for the task allocation problem, but most are limited to specific cases [10]. The use of evolutionary algorithms in scheduling, that apply evolutionary strategies from nature, allows for the fast exploration of the search space of possible schedules.…”

Strengths and weaknesses of genetic list scheduling for heterogeneous systems

“…The multiprocessor scheduling problem and related problems (like high-level synthesis) have been studied very extensively [1,4,10,11,14]. Unfortunately, the large number of problem variants makes direct comparison hardly possible.…”