Automated Parallelization of Timed Petri-Net Simulations

Nicol, David M.; Mao, Weizhen

doi:10.1006/jpdc.1995.1106

Cited by 26 publications

(5 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [12], the question of parallel simulation of timed Petri nets is solved using also a sophisticated partitioning of the Petri net to distribute its nodes on the computation units (cpu + memory), and a complex communication protocol to synchronise the distributed timed execution in order to ensure that it remains globally correct. The problem solved is substantially distinct from ours: [12] distributes a timed uncoloured Petri net and ensures the synchronisation the timed executions of its resulting parts, while we distribute the computation that arises from the execution of a centralised untimed coloured Petri net. We end up with a much simpler approach that has probably a much lower overhead and can be executed even on a modest multi-core cpu while [12] is designed for distributed-memory parallel computers.…”

Section: Related Workmentioning

confidence: 99%

“…The problem solved is substantially distinct from ours: [12] distributes a timed uncoloured Petri net and ensures the synchronisation the timed executions of its resulting parts, while we distribute the computation that arises from the execution of a centralised untimed coloured Petri net. We end up with a much simpler approach that has probably a much lower overhead and can be executed even on a modest multi-core cpu while [12] is designed for distributed-memory parallel computers.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Faster Simulation of (Coloured) Petri Nets Using Parallel Computing

Pommereau

Houssaye

2017

Application and Theory of Petri Nets and Concurrency

View full text Add to dashboard Cite

Fast simulation, i.e., automatic computation of sequential runs, is widely used to analyse Petri nets. In particular, it enables for quantitative statistical analysis by observing large sets of runs. Moreover, fast simulation may be used to actually run a Petri net model as a (prototype) implementation of a system, in which case such a net would embed fragments of the code of the system. In both these contexts, being able to perform faster simulation is highly desirable. In this paper, we propose a way to accelerate fast simulation by exploiting parallel computing, targeting both the multi-core cpus available nowadays in every laptop or workstation, and larger parallel computers including those with distributed memory (clusters). We design an algorithm to do so and assess in particular its correctness and completeness through its formal modelling as a Petri net whose state space is analysed. We also present a benchmark of a prototype implementation that clearly shows how our algorithm effectively accelerates fast simulation, in particular in the case of large concurrent coloured Petri nets, which is precisely the kind of nets that are usually slow to simulate.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Faster Simulation of (Coloured) Petri Nets Using Parallel Computing

Pommereau

Houssaye

2017

Application and Theory of Petri Nets and Concurrency

View full text Add to dashboard Cite

show abstract

“…Nicol and Mao [43] proposed methods for synchronizing and load balancing parallel timed petri-nets (PTPN) simulations, both static and dynamic. Their algorithm first arranges the LPs in a linear chain, then partitions the chain in as many contiguous sub-chains as there are processors, mapping one sub-chain per processor.…”

Section: Related Workmentioning

confidence: 99%

Reducing null messages overhead through load balancing in conservative distributed simulation systems

Boukerche

Das

2004

Journal of Parallel and Distributed Computing

View full text Add to dashboard Cite

“…Nicol and Mao raised a method based on time petri net and nodes combination mechanism [3] . The main concept of the method is the nodes combination and developing line links,nodes which having big communication spending come to be adjacent or at least near from each other.…”

Section: The Improved Partitioning Algorithm On the Issue Of Procesmentioning

confidence: 99%

Distributed Processing Based on Timed Petri Nets

Fang

Zhang

Yin

2007

Third International Conference on Natural Computation (ICNC 2007) Vol V

View full text Add to dashboard Cite

At present, in the design and analysis of discrete event systems, the parallel or distributed simulation mechanism is adopted to make these models occur concurrently , then the problem will be easy to be solved, the validation of their models is often addressed via simulation. Lookahead computation is a good method that improves the distributed simulation performance of Timed Transition Petri Nets (TTPN). Extended Timed Petri Nets (ETTPN) is extended in time based on TTPN, it meet Lookahead requirements, and use the Lookahead to analyze the ETTPN model for finding the concurrency and blocking structure, thereby making certain the logical process (LP). Based on the specialties of Lookahead, the Lookahead was applied in parallel simulation, and acquire the sufficient condition about the ETTPN model existing concurrency. According to the condition, parallel program can be partitioned into several logical processes, and the partition algorithm about distributed processing is avail. In order to reduce error rate,a improved mapping algorithm is presented.

show abstract

Automated Parallelization of Timed Petri-Net Simulations

Cited by 26 publications

References 28 publications

Faster Simulation of (Coloured) Petri Nets Using Parallel Computing

Faster Simulation of (Coloured) Petri Nets Using Parallel Computing

Reducing null messages overhead through load balancing in conservative distributed simulation systems

Distributed Processing Based on Timed Petri Nets

Contact Info

Product

Resources

About