Evaluation of parallel particle swarm optimization algorithms within the CUDA™ architecture

  title={Evaluation of parallel particle swarm optimization algorithms within the CUDA{\texttrademark} architecture},
  author={Luca Mussi and Fabio Daolio and Stefano Cagnoni},
  journal={Inf. Sci.},

Figures and Tables from this paper

Adaptive Particle Swarm Optimization with Heterogeneous Multicore Parallelism and GPU Acceleration
A heterogeneous approach mitigates the time complexity of PSO adaptations, suggesting that other time-intensive stochastic methods can also benefit from the techniques proposed here.
Dynamic particle swarm optimization with heterogeneous multicore parallelism and GPU acceleration
Heterogeneous high-performance computing is proposed as a way to mitigate the time complexity of dynamic PSO adaptions, and results on high-dimensional “moving-peaks” functions show that high speedups can be obtained through making use of different high- performance components on commodity hardware.
Accelerating parallel particle swarm optimization via GPU
A GPU-accelerated PSO (GPSO) algorithm is proposed by using a thread pool model and implement GPSO on a GPU, a promising method for tackling high-dimensional and difficult optimization problems using a low-cost and many-core GPU system.
A Survey on GPU-Based Implementation of Swarm Intelligence Algorithms
This paper presents a comprehensive review of GPU-based parallel SIAs in accordance with a newly proposed taxonomy and novel criteria are proposed to evaluate and compare the parallel implementation and algorithm performance universally.
High-Dimensional Adaptive Particle Swarm Optimization on Heterogeneous Systems
This paper explores the efficacy of employing other types of parallel hardware for PSO and provides another demonstration that "supercomputing on a budget" is possible when subtasks of large problems are run on hardware most suited to these tasks.
Performance Evaluation of Parallel Particle Swarm Optimization for Multicore Environment
The proposed algorithm is applied to the standard optimization test set CEC (Congress on Evolutionary Computation) 2014 and gave good results compared to the previous algorithm, and the execution time of Shared-PSO is more efficient than the serial PSO’s.
Scheduling Using Multiple Swarm Particle Optimization with Memetic Features on Graphics Processing Units
This work investigates the performance of a highly parallel Particle Swarm Optimization (PSO) algorithm implemented on the graphics processing unit (GPU) and shows that the GPU offers a high degree of performance and achieves a maximum of 37 times speedup over a sequential implementation when the problem size in terms of tasks is large and many swarms are used.
Implementation of Parallel Simplified Swarm Optimization in CUDA
The time complexity of Parallel Simplified Swarm Optimization (PSSO) based on the CUDA platform has successfully reduced by an order of magnitude of N, and the problem of resource preemption was avoided entirely.
A Survey on Parallel Particle Swarm Optimization Algorithms
Proposed work presents a comprehensive and systematic survey of the studies on PPSO algorithms and variants along with their parallelization strategies and applications.
A CUDA Implementation of the Standard Particle Swarm Optimization
This paper presents a good implementation for the Standard Particle Swarm Optimization (SPSO) on a GPU based on the CUDA architecture, which uses coalescing memory access and demonstrates that the GPU algorithm runs about maximum 46 times faster than the corresponding CPU algorithm.


GPU-based parallel particle swarm optimization
  • You Zhou, Ying Tan
  • Computer Science
    2009 IEEE Congress on Evolutionary Computation
  • 2009
A novel parallel approach to run standard particle swarm optimization (SPSO) on Graphic Processing Unit (GPU) is presented, which shows special speed advantages on large swarm population applications and hign dimensional problems, which can be widely used in real optimizing problems.
Swarm's flight: Accelerating the particles using C-CUDA
An implementation of the Particle Swarm Optimization (PSO) algorithm in C-CUDA is provided to show how optimization algorithms inspired by Swarm Intelligence can take profit from this technology.
Parallel asynchronous particle swarm optimization
This study introduces a parallel asynchronous PSO (PAPSO) algorithm to enhance computational efficiency and exhibits excellent parallel performance when a large number of processors is utilized and either heterogeneity exists in the computational task or environment, or the computation‐to‐communication time ratio is relatively small.
A Parallel Particle Swarm Optimization Algorithm with Communication Strategies
A parallel version of the particle swarm optimization (PPSO) algorithm together with three communication strategies which can be used according to the independence of the data, which demonstrates the usefulness of the proposed PPSO algorithm.
Parallelism and evolutionary algorithms
A modern vision of the parallelization techniques used for evolutionary algorithms (EAs) and provides a highly structured background relating to PEAs to make researchers aware of the benefits of decentralizing and parallelizing an EA.
Hardware-oriented Adaptation of a Particle Swarm Optimization Algorithm for Object Detection
It is shown how the intrinsic modularity of the algorithm permits to define a general core, independent of the specific application, which implements object search, along with a simple application specific-module, which implementing a problem-dependent fitness function makes the system easily reconfigurable when switching between different object detection applications.
Empirical assessment of the effects of update synchronization in Particle Swarm Optimization
It is shown that a sync hronous update of the social attractors, which is necessary when parallel versio ns of PSO are implemented, may influence the effectiveness of the algorithm, and the ‘global best’ topology is sensitive to the update, especially in the presence of high-dimensional search spaces.
Defining a Standard for Particle Swarm Optimization
A standard algorithm is defined here which is designed to be a straightforward extension of the original algorithm while taking into account more recent developments that can be expected to improve performance on standard measures.
Asynchronous multiple objective particle swarm optimisation in unreliable distributed environments
This paper examines the performance characteristics of both asynchronous and synchronous parallel particle swarm optimisation algorithms in heterogeneous, fault-prone environments, suggesting that at least partly asynchronous algorithms should be used in real-world environments where faults can regularly occur.