APPLICATIONS OF EVOLUTIONARY STRATEGIES TO FINE-GRAINED TASK SCHEDULING
Ajay Kumar Gupta, Garrison W. Greenwood · Parallel Processing Letters · 1996
Embedding task graphs onto hypercubes is a difficult problem. When the embedding is one-to-one, schedule length is strongly influenced by dilation. Therefore, it is desirable to find low dilation embeddings. This paper describes a heuristic embedding technique based upon evolutionary strategies. The technique has been extensively investigated using task graphs which are trees, forests, and butterflies. In all cases the technique has found low dilation embeddings.