Performance Analysis of a Parallel Discrete Model for the Simulation of Laser Dynamics

Guisado, J. L.; Vega, Francisco Fernández de; Iskra, Kamil

doi:10.1109/icppw.2006.62

Cited by 4 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…14. Given that large CA sizes might require the use of swap memory of the operating systems, which would greatly decrease the whole performance of the system, keeping us from correctly analyzing runtime, we have employed relatively small CA sizes (interested readers can also see [11]). The figure shows that the use of a load balancing strategy results in a good performance improvement for all system sizes within the studied ranges.…”

Section: Resultsmentioning

confidence: 99%

“…In this section, we describe the parallel implementation of the previous CA model and study its performance and scalability running on a small computer cluster (interested readers can refer to [9], [10], [11] and [12] for a larger description of results obtained). We begin by reviewing previous approaches to parallel implementations of CA models.…”

Section: Parallel Ca Based Simulation Of the Lasermentioning

confidence: 99%

See 1 more Smart Citation

Laser Dynamics Modelling and Simulation: An Application of Dynamic Load Balancing of Parallel Cellular Automata

Guisado

Morales

Guerra

et al. 2010

Studies in Computational Intelligence

View full text Add to dashboard Cite

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Parallel Ca Based Simulation Of the Lasermentioning

confidence: 99%

Laser Dynamics Modelling and Simulation: An Application of Dynamic Load Balancing of Parallel Cellular Automata

Guisado

Morales

Guerra

et al. 2010

Studies in Computational Intelligence

View full text Add to dashboard Cite

show abstract

“…In order to reduce the runtime of laser simulations with this model by taking advantage of its parallel nature, a parallel implementation of it for computer clusters (distributed-memory parallel computers), using the message-passing programming paradigm, was introduced in [20,21]. It showed a good performance on dedicated computer clusters [22] and also on heterogeneous non-dedicated clusters with a dynamic load balancing mechanism [23].…”

Section: Introductionmentioning

confidence: 99%

Developing Efficient Discrete Simulations on Multicore and GPU Architectures

et al. 2020

View full text Add to dashboard Cite

In this paper we show how to efficiently implement parallel discrete simulations on multicore and GPU architectures through a real example of an application: a cellular automata model of laser dynamics. We describe the techniques employed to build and optimize the implementations using OpenMP and CUDA frameworks. We have evaluated the performance on two different hardware platforms that represent different target market segments: high-end platforms for scientific computing, using an Intel Xeon Platinum 8259CL server with 48 cores, and also an NVIDIA Tesla V100 GPU, both running on Amazon Web Server (AWS) Cloud; and on a consumer-oriented platform, using an Intel Core i9 9900k CPU and an NVIDIA GeForce GTX 1050 TI GPU. Performance results were compared and analyzed in detail. We show that excellent performance and scalability can be obtained in both platforms, and we extract some important issues that imply a performance degradation for them. We also found that current multicore CPUs with large core numbers can bring a performance very near to that of GPUs, and even identical in some cases.

show abstract

Building Efficient Computational Cellular Automata Models of Complex Systems: Background, Applications, Results, Software, and Pathologies

Kroc

Morales

Guisado

et al. 2019

Advs. Complex Syst.

View full text Add to dashboard Cite

Cellular automaton models of complex systems (CSs) are gaining greater popularity; simultaneously, they have proven the capability to solve real scientific and engineering applications. To enable everybody a quick penetration into the core of this type of modeling, three real applications of cellular automaton models, including selected open source software codes, are studied: laser dynamics, dynamic recrystallization (DRX) and surface catalytic reactions. The paper is written in a way that it enables any researcher to reach the cutting edge knowledge of the design principles of cellular automata (CA) models of the observed phenomena in any scientific field. The whole sequence of design steps is demonstrated: definition of the model using topology and local (transition) rule of a cellular automaton, achieved results, comparison to real experiments, calibration, pathological observations, flow diagrams, software, and discussions. Additionally, the whole paper demonstrates the extreme expressiveness and flexibility of massively parallel computational approaches compared to other computational approaches. The paper consists of the introductory parts that are explaining CSs, self-organization and emergence, entropy, and CA. This allows readers to realize that there is a large variability in definitions and solutions of this class of models.

show abstract

Performance Analysis of a Parallel Discrete Model for the Simulation of Laser Dynamics

Cited by 4 publications

References 15 publications

Laser Dynamics Modelling and Simulation: An Application of Dynamic Load Balancing of Parallel Cellular Automata

Laser Dynamics Modelling and Simulation: An Application of Dynamic Load Balancing of Parallel Cellular Automata

Developing Efficient Discrete Simulations on Multicore and GPU Architectures

Building Efficient Computational Cellular Automata Models of Complex Systems: Background, Applications, Results, Software, and Pathologies

Contact Info

Product

Resources

About