parallel and distributed discrete-event simulation (PDES) is a critical technology for an important class of very large complicated simulation models. However, with few exceptions, the bulk of empirical work in PDES h...
详细信息
parallel and distributed discrete-event simulation (PDES) is a critical technology for an important class of very large complicated simulation models. However, with few exceptions, the bulk of empirical work in PDES has been on small models. Furthermore, synchronization behavior is frequently complicated, which makes it very difficult to analytically prove anything about the performance executing large models on large machines. Scalability analysis asks how the performance of a certain application behaves as the application problem size increases and the parallel architecture executing it increases.
The Hierarchical Tool HIT is a software tool for hierarchical modeling and performance evaluation of discrete event systems. Besides analytical and numerical solution techniques HIT provides the evaluation of models b...
详细信息
ISBN:
(纸本)0818679654
The Hierarchical Tool HIT is a software tool for hierarchical modeling and performance evaluation of discrete event systems. Besides analytical and numerical solution techniques HIT provides the evaluation of models by sequential simulation. Here we present concepts for optimistic distributedsimulation of HIT-models by partitioning them with respect to subhierarchies. The main goals of the concept being presented are the preservation of model structure even in lower levels of the realization (e.g. use of the process view of simulation throughout all levels of abstraction) and distribution transparency on the modeling level (homogeneous model specification for all solution techniques).
In this paper we revisit the notion of event simultaneity in the context of parallel and distributedsimulation. Although the simulation community has recognized this problem for years, it has focused mainly on the me...
详细信息
In this paper we revisit the notion of event simultaneity in the context of parallel and distributedsimulation. Although the simulation community has recognized this problem for years, it has focused mainly on the mechanics of breaking event-time ties and has neither measured its extent nor considered its implications. Extant simulators (both serial and parallel) prohibit simultaneity either by user-specified event priorities or by an arbitrary (but well-documented) tie-breaking mechanism. We shall show, theoretically and empirically, that these strategies may lead to an invalid simulation. In doing so, we shall introduce the threshold of event simultaneity and use it to understand the semantics of simultaneity.
One of the key factors for efficiency in distributedsimulation is the detection of model-inherent concurrency, which is related on the prediction of the future behavior of each logical simulation process. In this pap...
详细信息
One of the key factors for efficiency in distributedsimulation is the detection of model-inherent concurrency, which is related on the prediction of the future behavior of each logical simulation process. In this paper we present a generalization of traditional approaches to behavioral prediction which provides more accurate predictions in general and a high degree of scalability in terms of computational and communication overhead. We give a sequential implementation, prove its correctness using concepts from the analysis of real-time process networks and then show how these results can be used in distributedsimulation.
The notion of temporal uncertainty, expressed as the possibility for an event to occur in an interval of simulation time, rather than at a specific instant, has been recently proposed and exploited in order to enhance...
详细信息
ISBN:
(纸本)0769521118
The notion of temporal uncertainty, expressed as the possibility for an event to occur in an interval of simulation time, rather than at a specific instant, has been recently proposed and exploited in order to enhance the performance of parallel/distributedsimulation systems. In this paper we propose the concept of "spatial uncertainty" expressed as the possibility for a simulation event to occur in one of a set of points within the simulated system space. How to handle/exploit space uncertain events in an optimistic simulation system is discussed. Also, experimental results for optimistic simulations of a Personal Communication System (PCS) modeled with space uncertain events are reported These results show the ability of spatial uncertainty to increase the performance of the parallelsimulation system by providing a more flexible approach to synchronization.
The bubble algorithm evaluated in this paper assures message deadlock freedom in k-ary n-cube network without wing virtual channels. This algorithm is based both on a dimension order routing (DOR) and on a restricted ...
详细信息
ISBN:
(纸本)0769500595
The bubble algorithm evaluated in this paper assures message deadlock freedom in k-ary n-cube network without wing virtual channels. This algorithm is based both on a dimension order routing (DOR) and on a restricted injection policy extended to the dimension changes. An exhaustive comparison between the bubble mechanism and the classical deterministic virtual channels solution is presented here. For that purpose, the message router of both proposals has been designed by using VHDL descriptions and the Synopsys VLSI CAD tool. Additionally :formal models of the routers, based on colored Petri nets, have been carried out together with simulation techniques in order to assure the validation of the results and shorten the design cycle. The performance evaluation of n-dimension tori highlights the benefits of the bubble algorithm as both the temporal delay and the necessary silicon area of the message router ape reduced.
Although there exist many approaches for classification of computer architectures, no system is able to distinguish parallel computers adequately yet. The first part of this paper is a brief survey of the main charact...
详细信息
ISBN:
(纸本)0769500595
Although there exist many approaches for classification of computer architectures, no system is able to distinguish parallel computers adequately yet. The first part of this paper is a brief survey of the main characteristics of various parallel architecture concepts and several approaches of classification. We realized that the idea of defining a sharp classification system is questionable in the world of parallel computing. But we also recognized important structural similarities of computing systems. So we introduce a modeling system, called rho (recursive hierarchical objects), which allows to describe the structure Of various computing systems hierarchically. However we do not aim at a new classification system but at a scheme for modeling parallel architectures.
The Data Distribution Management (DDM) service is one of the six services provided in the Runtime Infrastructure (RTI) of High Level Architecture (HLA). Its purpose is to perform data filtering and reduce irrelevant d...
详细信息
ISBN:
(纸本)0769511058
The Data Distribution Management (DDM) service is one of the six services provided in the Runtime Infrastructure (RTI) of High Level Architecture (HLA). Its purpose is to perform data filtering and reduce irrelevant data communicated between federates. The two DDM schemes proposed for RTI, region-based and grid-based DDM, are oriented to send as little irrelevant data to subscribers as possible, but only manage to filter part of this information and some irrelevant data is still being communicated. In a previous paper [3], we employed intelligent agents to perform data filtering in HLA, implemented an agent-based DDM in RTI (ARTI) and compared it with the other two filtering mechanisms. This paper reports on additional experiments, results and analysis using two scenarios, the AWACS sensing aircraft simulation and the air traffic control simulation scenario Experimental results show that compared with other mechanisms, the agent-based approach communicates only relevant data and minimizes network communication, and is also comparable in terms of time efficiency. Some guidelines on when the agent-based scheme can be used are also given.
We present a new conservative event-synchronization protocol, time-based synchronization, for parallel discrete-event simulation of mobile ad hoc wireless networks. Simulators that use our protocol proceed at a scaled...
详细信息
ISBN:
(纸本)0769520367
We present a new conservative event-synchronization protocol, time-based synchronization, for parallel discrete-event simulation of mobile ad hoc wireless networks. Simulators that use our protocol proceed at a scaled version of real time and send messages that correspond only to transmissions in the simulated network. We show that such simulators can maintain a constant execution time even as the sizes of the networks that they simulate grow. Moreover we show that these simulators, when executed on a custom parallel architecture, are capable of simulating many networks faster than real time.
With parallel and Discrete Event simulation (PDES) techniques, the runtime performance of detailed wireless network simulation can be improved significantly without compromising fidelity of the simulation results. How...
详细信息
ISBN:
(纸本)0769521118
With parallel and Discrete Event simulation (PDES) techniques, the runtime performance of detailed wireless network simulation can be improved significantly without compromising fidelity of the simulation results. However modelling characteristics of wireless communications such as signal propagation and interference may severely hinder the potential speedup yielded by PDES. This paper proposes various optimization techniques to address three major concerns in achieving efficient parallel execution of wireless network simulation: i.e., (1) reducing communication and computation overhead of simulating signal propagation across multiple logical processes;(2) reducing synchronization overhead among logical processes;(3) minimizing event scheduling overhead within individual logical processes. These techniques have been implemented in a parallel version of GloMoSim and QualNet. The experimental results with mobile ad hoc networking scenarios demonstrate that the proposed optimization techniques can improve the performance of parallel wireless network simulation by up to an order of magnitude.
暂无评论