Benchmarking parallel simulation algorithms

Barriga, L.; Rönngren, Robert; Ayani, Rassul

doi:10.1109/icapp.1995.472248

Cited by 7 publications

(6 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have started assembling a benchmark suite of real models that will be complemented by SWG produced workloads. The suite currently includes an implementation of gate-level digital logic simulator, a sharks world model (Conklin, Cleary, and Unger 1990)) and the set of ping models proposed by Barriga (Barriga, Ronngren, and Ayani 1995). The circuits used for the digital-logic simulation are from the ISCAS'89 (CAD Benchmarking Lab, NCSU 1989) benchmark suite.…”

Section: Discussionmentioning

confidence: 99%

“…For the next experiment, WSL was used to represent the ping-pang models presented by Barriga (Barriga, Ronngren, and Ayani 1995). The results of scaling these benchmarks is shown in Figure 8 and Figure 9.…”

Section: Methodsmentioning

confidence: 99%

“…There are several empirical and analytical studies (Fujimoto 1987;Fujimoto 90;Barriga, Ronngren, and Ayani 1995;Samadi 1985;Kumar 1989) of the performance of PDES algorithms. Most of these studies appear in the context of evaluating the impact a particular simulator improvement on the performance.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

A framework for performance analysis of parallel discrete event simulators

Balakrishnan¹,

Frey²,

Abu-Ghazaleh³

et al. 1997

Proceedings of the 29th Conference on Winter Simulation - WSC '97

View full text Add to dashboard Cite

A framework for performance analysis of parallel discrete event simulators is presented. The centerpiece of this framework is a platform-independent Workload Specification Language (WSL). WSL is a language that allows the characterization of simulation models using a set of fundamental performancecritical parameters. WSL also implements a facility for representing real models. For each simulator to be tested, a WSL translator is used to generate synthetic platform-specific simulation models that conform to the performance characteristics captured by the WSL description. Accordingly, sets of portable simulation models that explore the effects of the different parameters, individually or collectively, on the performance can be constructed. The construction of the workload simulation models is assisted using a Synthetic Workload Generator (SWG). The utility of the system is demonstrated with the generation of a representative set of experiments. The described framework can be used to create a standard benchmark suite that consists of a mixture of real simulation models, selected from different application domains, and synthetic models generated by SWG.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A framework for performance analysis of parallel discrete event simulators

Balakrishnan¹,

Frey²,

Abu-Ghazaleh³

et al. 1997

Proceedings of the 29th Conference on Winter Simulation - WSC '97

View full text Add to dashboard Cite

show abstract

“…Barriga et al [3] have proposed a simple, strictly deterministic set of tests for a DSD system implemented on the basis of the Time Warp optimistic approach. By analogy the authors chose the following tests: 1.…”

mentioning

confidence: 99%

“…Three classes of tests are used to evaluate the performance of multiprocessor architectures: realistic applications, kernels, and cycles [3]. These same classes can also be used for DSD.…”

mentioning

confidence: 99%

Distributed simulation design ofMC-models on networks of work stations

Voznesenskaya¹,

Fakanov²

1998

Comput Math Model

View full text Add to dashboard Cite

This paper is devoted to the basic problems of organizing distributed simulation design (DSD). We study the formulation of the DSD problem of MC-models on networks of work stations. We describe the implementation of a DSD system with a conservative Chandy-Misra synchronization algorithm and discuss the problems that arise in doing so.One figure, 2 tables. Bibliography: 13 titles.Introduction. In this paper we study the problem of organizing parallel execution of programs of simulation models for the case of discrete-event simulation modeling [6]. The purpose of distributed simulation design (DSD) is to shorten as much as possible the actual time for executing the model. The characteristic that distinguishes simulation design programs from other types of programs is that the behavior of all processes in the model must occur in a unified model time. It is assumed that the processes of the modeling program are carried out on processors that lack a unified timer or any special synchronization apparatus that could substitute for one. Maintaining the unity of the model time is the main problem ofa DSD system.

show abstract