In many practical situations, in particular in many bioinformatics problems, the amount of required computations is so huge that the only way to perform these computations in reasonable time is to distribute them between multiple processors.The more processors we engage, the faster the resulting computations; thus, in addition to processor exclusively dedicated to this job, systems often use idle time on other processors. The use of these otherwise engaged processors adds additional uncertainty to computations.How should we schedule the computational tasks so as to achieve the best utilization of the computational resources?Because of the presence of uncertainty, this scheduling problem is very dif cult not only to solve but even to formalize (i.e., to describe in precise terms). In this paper, we provide the rst steps towards formalizing and solving this scheduling problem.
II. SUPERCOMPUTING IN THE PASTIn this paper, we will analyze scheduling in global computing. To explain the idea (and the necessity) of global computing, it is important to explain how the concept of supercomputing has evolved in the last decades.In the past, the ability to use supercomputers to simulate such things as nuclear weapons design was an important part of military confrontation. As a result, special classi ed technology was used to design supercomputers, technology that was not allowed on regular individual computers.