Back to Scheduling Models

Abstract

In the preceding chapters we presented some technical background of scheduling in parallel systems. This included both the “technology” of mathematical analysis tools and the technology of parallel processing. Four different views of scheduling for parallel processing were analyzed in the form of four different scheduling models. In this chapter, we will make some remarks on the models and algorithms for scheduling parallel computations. We will use previous chapters as the basis for our considerations. The goal of this chapter is not to criticize the results presented earlier in the book, but to draw conclusions and generalize the knowledge beyond the limits of particular scheduling models. Probably these conclusions cannot be called enlightening, but we believe that it is worthwhile to present them so that the previous discussions are put into a wider context. We also hope that these observations may be helpful in future considerations on scheduling models, problems, and algorithms.

Let us return to Fig. 1.2. It illustrates the relation between real scheduling problems, their models, theoretical scheduling problems, algorithms, and schedules. Figure 1.2 also corresponds with the process of transforming knowledge on real scheduling problem into a schedule. All the steps in the development of a schedule have their peculiarities. In the rest of this chapter we will discuss some pitfalls in the above process of developing schedules for parallel applications.