A Comparative Study of Some Priority Queues Suitable for Implementation of the Pending Event Set1

Implementation of the pending event set (PES) is often crucial to the execution speed of a simulation. Parallel access implementation of the PES is a possible means of gaining performance improvement in discrete event simulation. In this paper a comparative study of some sequential and parallel access implementations of the PES is presented, these include linked lists, the Calendar Queue, the Lazy Queue, the Skew Heap and the implicit binary heap. All the parallel access implementations have a potential for an O(1) access time. A comparison of the performance of these implementations on a shared memory multiprocessor is presented. From these experiments some guide-lines have been compiled for choosing priority queue implementations for the PES. We also show that the parallel access implementations of the priority queues considered in this paper only offers what could be characterized as limited consitency. This fact may make these implementations less suitable for implementation of the PES in conservative simulators.