A model for parallel simulation of distributed shared memory

Abstract

We present an execution model for parallel simulation of a distributed shared memory architecture. The model captures the processor-memory interaction and abstracts the memory subsystem. Using this model we show how parallel, on-line, partially-ordered memory traces can be correctly predicted without interacting with the memory subsystem. We also outline a parallel optimistic memory simulator that uses these traces, finds a global order among all events, and returns correct data and timing to each processol: A first evaluation of the amount of concurrency that our model can extract for an ideal multiprocessor shows that processors may execute relatively long instruction sequences without violating the causality constraints. Howevel; parallel simulation efJiciency is highly dependent on the memory consistency model and the application characteristics.

The Research of PAS's Graphical Configuration Simulation Based on Fluid Network Theory

“…The constraints described above reflect the topological simulation model, but we have to establish a dynamic simulation model M to respond to the implementation of processes and state of network [12,13]. M sends and receives critical information through the logical process (LP), expressed as (1):…”

A new scheduling method for parallel discrete-event simulation

“…Our concept is conservative and non-blocking and suggests a tradeoff between the computation overhead and the memory required for node synchronization. As in [1,2,6,8] we also base our approach on distances between processes. However, in order to adapt to parallel computers with message passing we avoid all barrier synchronization.…”

“…Most previous approaches [1,2,6,7,8] use a simple scheduling method where the execution order of ready events is arbitrary. Our method however is based on an algorithm which optimizes the order in which the events are executed by the nodes in respect to effective node synchronization.…”