Nature-Inspired Meta-Heuristics on Modern GPUs: State of the Art and Brief Survey of Selected Algorithms

Krömer, Pavel; Platoš, Jan; Snåšel, Václav

doi:10.1007/s10766-013-0292-3

Cited by 30 publications

(12 citation statements)

References 87 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This field of computer engineering research is called General-Purpose computing on Graphics Processing Units (GPGPU). GPU co-processors are constructed to accelerate parallel floating-point operations massively (Krömer et al, 2014). As stated by Owens et al (2008), the current development of GPUs provides the opportunity to tackle computationally demanding and complex problems and represents a low-cost solution.…”

Section: Parallelization and Distributed Computingmentioning

confidence: 99%

A GPU-based Parallelization Approach to conduct Spatially-Explicit Uncertainty and Sensitivity Analysis in the Application Domain of Landscape Assessment

Erlacher¹,

Jankowski²,

Blaschke³

et al. 2017

giforum

View full text Add to dashboard Cite

This paper illustrates a CUDA GPU-based concept to accelerate the computationally intensive calculations of performing spatially-explicit uncertainty and sensitivity analysis in multi-criteria decision-making models. Uncertainty and sensitivity analysis is a two-step approach to validating the robustness of spatial-and non-spatial model solutions. The uncertainty analysis quantifies the variability of model outcomes, while the sensitivity analysis accounts for the contributions of model inputs to the overall model output variability. The proposed solution is applicable for large-scale spatial problems that incorporate millions of alternatives and hundreds of thousands of simulation runs. Furthermore, this GPU-based concept represents a low-cost approach in comparison to high-performance computing that incorporates super computers. Additionally, the concept allows the integration of different decision rules (e.g. simple additive weighting, ideal point, ordered weighting averaging, or analytical hierarchy process) in order to evaluate the performance of the alternatives involved. The proposed approach was tested on a landscape assessment example in order to identify the variability of the model outcomes with respect to the criteria 'Compactness', 'Mean Patch Area', 'Relief Energy' and 'Variety' that define landscape diversity.

show abstract

Section: Parallelization and Distributed Computingmentioning

confidence: 99%

A GPU-based Parallelization Approach to conduct Spatially-Explicit Uncertainty and Sensitivity Analysis in the Application Domain of Landscape Assessment

Erlacher¹,

Jankowski²,

Blaschke³

et al. 2017

giforum

View full text Add to dashboard Cite

show abstract

“…The GPU accelerated ACO was successfully used by Cekmez et al [6] to solve the path planning problem of an Unmanned Aerial Vehicle (UAV). A survey of recent advances in applying the GPUs to speedup other metaheuristic algorithms can be found in [18,22,26].…”

Section: Related Workmentioning

confidence: 99%

The GPU-based parallel Ant Colony System

Skinderowicz¹

2016

Journal of Parallel and Distributed Computing

View full text Add to dashboard Cite

The Ant Colony System (ACS) is, next to Ant Colony Optimization (ACO) and the MAX-MIN Ant System (MMAS), one of the most efficient metaheuristic algorithms inspired by the behavior of ants. In this article we present three novel parallel versions of the ACS for the graphics processing units (GPUs). To the best of our knowledge, this is the first such work on the ACS which shares many key elements of the ACO and the MMAS, but differences in the process of building solutions and updating the pheromone trails make obtaining an efficient parallel version for the GPUs a difficult task. The proposed parallel versions of the ACS differ mainly in their implementations of the pheromone memory. The first two use the standard pheromone matrix, and the third uses a novel selective pheromone memory. Computational experiments conducted on several Travelling Salesman Problem (TSP) instances of sizes ranging from 198 to 2392 cities showed that the parallel ACS on Nvidia Kepler GK104 GPU (1536 CUDA cores) is able to obtain a speedup up to 24.29x vs the sequential ACS running on a single core of Intel Xeon E5-2670 CPU. The parallel ACS with the selective pheromone memory achieved speedups up to 16.85x, but in most cases the obtained solutions were of significantly better quality than for the sequential ACS.

show abstract

“…These errors can cause loss of money and innocent human lives [1]. For example, in April 24 1994, a China airline airbus A-300 crashed, due to a software bug, resulting the death of 264 innocent lives [2,3]. Another famous incident was reported in April 1999, where a small software bug in a military satellite was behind a $1.2 billion loss: one of the costliest unmanned accidents in the history of Cape Canaveral launches [4,5].…”

Section: Introductionmentioning

confidence: 99%

Frameworks for Performing on Cloud Automated Software Testing Using Swarm Intelligence Algorithm: Brief Survey

Hossain¹,

Abufardeh²,

Kumar³

2018

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

Nature-Inspired Meta-Heuristics on Modern GPUs: State of the Art and Brief Survey of Selected Algorithms

Cited by 30 publications

References 87 publications

A GPU-based Parallelization Approach to conduct Spatially-Explicit Uncertainty and Sensitivity Analysis in the Application Domain of Landscape Assessment

A GPU-based Parallelization Approach to conduct Spatially-Explicit Uncertainty and Sensitivity Analysis in the Application Domain of Landscape Assessment

The GPU-based parallel Ant Colony System

Frameworks for Performing on Cloud Automated Software Testing Using Swarm Intelligence Algorithm: Brief Survey

Contact Info

Product

Resources

About