Further results using the overhead model for parallel systems
Horace P. Flatt · IBM Journal of Research and Development · 1991
A performance model that takes into consideration the overhead incurred in the use of a parallel system is used to show that the maximum value of the speedup achieved by the parallel system for a fixed problem may be much smaller than the number of processors required to achieve that value. It is also shown that under certain conditions, the problem size may be varied so as to achieve a speedup closely approximating the number of processors used.