Dynamic load assignment of real-time tasks in distributed memory multiprocessors

In this paper, we consider a scalable distributed-memory architecture for w hich we propose a problem representation that assigns real-time tasks on th e processing units of the architecture to maximize deadline compliance rate . Based on the selected problem representation, we derive an algorithm that dynamically schedules real-time tasks on the processors of the distributed architecture. The algorithm uses a formula to generate the adequate schedu ling time so that deadline loss due to scheduling overhead is minimized whi le deadline compliance rate is being maximized. The technique we propose pr oved to be correct in the sense that the delivered solutions are not obsole te, i.e., the assigned tasks to working processors are guaranteed to meet t heir deadlines once executed. The correctness criterion is obtained based o n our technique to control the scheduling time. To evaluate the performance of the algorithms that we propose, we provide a number of experiments thro ugh a simulation study. We also propose an implementation of our algorithms in the context of scheduling real-time transactions on an Intel-Paragon di stributed-memory multiprocessor. The results of the conducted experiments s how interesting performance trade-offs among the candidate algorithms.