A "conservative" approach to parallelizing the Sharks World simulation

This paper describes how we parallelized a benchmark problem for parallel simulation, the Sharks World. The solution we describe is conservative, in the sense that no state information is saved, and no "rollbacks" occur. Our approach illustrates both the principal advantage and principal disadvantage of conservative parallel simulation. The advantage is that by exploiting lookahead we find an approach that dramatically improves the serial execution time, and also achieves excellent speedups. The disadvantage is that if the model rules are changed in such a way that the lookahead is destroyed, it is difficult to modify the solution to accommodate the changes. *Research was supported by the National Aeronautics and Space Administration under NASA Contract No. NAS1-18605 while the author was in residence at the Institute for Computer Applications in Science and Engineering (ICASE), NASA Langley Research Center, Hampton, VA 23665. Research also supported in part by NASA grant NAG-l-1060 and by NSF Grant ASC 8819373.