We investigate the extent to which the BSP model can be applied to the simulation of complex and large asynchronous systems. We focus on "direct" BSP algorithms wherein we distinguish iterations composed of two phases: (i) the parallel phase where each processor is allowed to work sequentially and asynchronously during varying periods of the simulated time, and (ii) the synchronisation phase where pre-defined actions are taken in order to decide the extent of the next parallel phase. This basic idea is applied to the simulation of networks of logical processes. 1 Introduction Our aim is to perform the BSP simulation of a set of N logical processes (LPs) that interact with each other through timestamped messages [7, 15]. The simulation goal consists of processing a total of M messages on a P-processor BSP computer [18]. The messages represent events scheduled to take place in the system at discrete points in the simulated time. For example, if LP j is simulating a "server" j in a queui...

We use an old idea of tournament based complete binary tree (CBT) to implement parallel priority queues (PQs). We show that this data structure enables a more efficient implementation of the operations extract-min and insert in terms of communications and synchronizations among processors than similar operations on the implicit heap. In most cases we only improve the asymptotic bounds on constant factors. However, some operations can be twice faster using simpler parallel algorithms upon the CBT. 1 Data structure and basic operations Every item stored in the PQ consists of a priority value and an indentifier. We associate every leaf of the CBT with one item, and use the internal nodes to maintain a continuous binary tournament among the items. A match, at internal node n, consists of determining the item with greater priority (less numerical value) between the two children of n and writing the identifier of the winner in n. The tournament is made up of a set of matches played in ever...

The bulk-synchronous parallel (BSP) model of computing has been proposed to enable the development of portable software which achieves scalable performance across diverse parallel architectures. A number of applications of computing science have been demonstrated to be efficiently supported by the BSP model in practice.