Running Particle Swarm Optimization on Graphic Processing Units

Bastos-Filho, Carmelo J. A.; Oliveira, Marcos; Nascimento, Débora

doi:10.5772/14694

Cited by 5 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There have been several successful attempts to parallelise the PSO on GPU [27][28][29][30]. These include a Beowulf cluster PSO [28], the IPPSO [29], a CUDA PSO [27], and also a Lévy flight CUDA PSO [31].…”

Section: Position Vector Is Within Bounds End Formentioning

confidence: 99%

“…Typically with the architectural restrictions imposed by CUDA, some compromises must be made. One such issue which is not as prominent in serial versions of these algorithms is the problem of random deviates [30]. For the trivial parallelisation of the PSO on GPU, it makes sense to generate random deviates on the host, and copy these onto the GPU in tandem.…”

Section: Position Vector Is Within Bounds End Formentioning

confidence: 99%

See 1 more Smart Citation

Particle Swarm-based Meta-Optimising on Graphical Processing Units

Husselmann¹,

Hawick²

2013

Modelling, Identification and Control / 801: Advances in Computer Science

View full text Add to dashboard Cite

Optimisation (global minimisation or maximisation) of complex, unknown and non-differentiable functions is a difficult problem. One solution for this class of problem is the use of meta-heuristic optimisers. This involves the systematic movement of n-vector solutions through ndimensional parameter space, where each dimension corresponds to a parameter in the function to be optimised. These methods make very little assumptions about the problem. The most advantageous of these is that gradients are not necessary. Population-based methods such as the Particle Swarm Optimiser (PSO) are very effective at solving problems in this domain, as they employ spatial exploration and local solution exploitation in tandem with a stochastic component. Parallel PSOs on Graphical Processing Units (GPUs) allow for much greater system sizes, and a dramatic reduction in compute time. Meta-optimisation presents a further super-optimiser which is used to find appropriate algorithmic parameters for the PSO, however, this practice is often overlooked due to its immense computational expense. We present and discuss a PSO with an overlaid super-optimiser also based on the PSO itself.

show abstract

Section: Position Vector Is Within Bounds End Formentioning

confidence: 99%

Section: Position Vector Is Within Bounds End Formentioning

confidence: 99%

Particle Swarm-based Meta-Optimising on Graphical Processing Units

Husselmann¹,

Hawick²

2013

Modelling, Identification and Control / 801: Advances in Computer Science

View full text Add to dashboard Cite

show abstract

“…Many evolutionary algorithms have been implemented on GPUs showing tremendous speedup including particle swarm optimization (PSO) [2][3][4][5][6][7][8][9][10] and differential evolution (DE) [11][12][13][14].…”

Section: Introductionmentioning

confidence: 99%

Implementing a population-based harmony search algorithm on graphic processing units

AlAjmi

El-Abd

2014

2014 IEEE 27th Canadian Conference on Electrical and Computer Engineering (CCECE)

View full text Add to dashboard Cite

show abstract

“…GPUs have already been used extensively in the literature for many fields of research including parametric evolutionary optimisers [1,18,36], machine learning [2], genetic programming [5,13,23,24] and agent-based modelling [19] among others. While GPU hardware provides for a potentially high performance platform, it also introduces several peculiarities due to the architecture, which was historically inspired from high-throughput processing of pixel data.…”

Section: Introductionmentioning

confidence: 99%

Intelligent Individual Agent-based Simulation of Photobioreactors and Growth Control

Husselmann¹,

Hawick²

2013

Power and Energy / 807: Intelligent Systems and Control / 808: Technology for Education and Learning

View full text Add to dashboard Cite

Photobioreactors offer an efficient and controllable environment from which many biomaterial-based products can be manufactured naturally. For example, the cultivation of the algae H. pluvialis, results in a carotenoid known as Astaxanthin, which is a highly valuable pigment and powerful antioxidant. The demand for naturally-produced Astaxanthin is much higher than synthetic, and the process by which this algae is cultivated is therefore important. We develop a discrete agent-based model that can be used to test the control processes for growing and harvesting such a bio product. We experiment with a variant of the Photosynthetic Factory model to improve cell division and hence growth kinetics. We employ parallel computing techniques to implement simulations of large numbers of control agents on graphical processing units. We discuss the implications of stochasticity, and propose a metric with which to balance cultivation time against fill rates of a stochastic data-parallel, bubble-column photobioreactor simulation.

show abstract

Running Particle Swarm Optimization on Graphic Processing Units

Cited by 5 publications

References 15 publications

Particle Swarm-based Meta-Optimising on Graphical Processing Units

Particle Swarm-based Meta-Optimising on Graphical Processing Units

Implementing a population-based harmony search algorithm on graphic processing units

Intelligent Individual Agent-based Simulation of Photobioreactors and Growth Control

Contact Info

Product

Resources

About