On superlinear speedups (Q1179219)

\textit{R. Janssen} [Parallel Comput. 4, 211-213 (1987; Zbl 0641.68070)] proposed an algorithm for which the use of \(n\) processors can reduce computer time by more than a factor of \(n\). It is shown that in the example that Janssen offered the superlinear speedup was possible only due to inefficient programming of the algorithm on a single processor. Yet Janssen's claim is correct, as shown by another example.