Multiprocessor scheduling with interprocessor communication delays

Evolving toward an Optimal Scheduling Solution through Adaptivity

“…Typically, the aim is to minimize total execution time of the application [3,4,10], or the total cost of the communication delay and load balance [11][12][13]. The scheduling algorithm and the scheduling objective determine the critical attributes associated with the tasks and processors in the task and processor model, respectively.…”

“…PET is based on the list-scheduling algorithm ERT [4]. At any instant, each schedulable task or free task (i.e., those tasks for which all tasks on which it depends have been distributed onto processors), in the application program is assigned a priority value based on its ''earliest start time.''…”

“…The scheduling problem has been proved to be NP-complete [2]. Various heuristics [3,4] and software tools [4,5] have been developed to pursue a suboptimal solution within acceptable computation complexity bounds. A detailed survey of such systems is found in [6,7].…”

A Task Duplication Based Scalable Scheduling Algorithm for Distributed Memory Systems

“…The earliest scheduling algorithms were priority-based algorithms [1,14,19,23,24]. These algorithms assign a priority to each task of the DAG and whenever a free processor is available, the task with the highest priority among all the ready tasks (i.e., tasks for which all the predecessor tasks have completed their execution) is assigned to the free processor.…”

Scheduling in a dynamic heterogeneous distributed system using estimation error

“…Two immediate mode schedulers have been implemented, lightest-loaded (LL) which assigns tasks to the lightest loaded processors, and earliest first [27] (EF) which assigns tasks to the processors which will finish processing them earliest. Round robin (RR), is the simplest and one of the most commonly used schedulers.…”