Acceleration of Genetic Algorithm on GPU CUDA Platform

Janssen, Dylan M.; Liew, Alan Wee‐Chung

doi:10.1109/pdcat46702.2019.00047

Cited by 6 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this article, we accelerate the evolution of the coarse‐grained island model GA (IMGA) by exploiting the parallel computing capability of GPUs based on the CUDA platform. This study extends our previous work 5 where we have extended our algorithm for numerical optimization problems, perform optimization of larger dimensions, and removed all asynchronous operations so that our algorithm can be repeated reliably. We also discuss and compare IMGA execution on differing hardware, focus on finding a solution rather than executing a set number of generations, and finally discuss the robustness of our proposed algorithm on both CPU and GPU hardware.…”

Section: Introductionsupporting

confidence: 64%

Graphics processing unit acceleration of the island model genetic algorithm using the CUDA programming platform

Janssen

Pullan

Liew

2021

Concurrency and Computation

View full text Add to dashboard Cite

Genetic algorithms are a practical approach for finding near‐optimal solutions for nondeterministic polynomial‐hard problems. In this work we exploit the parallel processing capability of graphics processing units and Nvidia's CUDA programming platform to accelerate the island model genetic algorithm by modifying the evolutionary operations to fit the hardware architecture and have successfully achieved significant computational speedups.

show abstract

Section: Introductionsupporting

confidence: 64%

Graphics processing unit acceleration of the island model genetic algorithm using the CUDA programming platform

Janssen

Pullan

Liew

2021

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…All these results show that the mean absolute error is smaller, in the order shown in Table A. 18. From these figures, the Rational 2 and the Rational 3 functions both well-fitted to the real speed-up functions for all problems, and they obtain a similar prediction curve.…”

Section: Appendix A3 Model Selection For the Speed-upmentioning

confidence: 52%

“…We can distinguish two kinds of analysis for parallel metaheuristics: on the one hand, some papers analyzed the effect of the physical parallel platform (e.g., GPUs, multicores, cloud), while on the other hand, other works studied the design and the influence of the parameters in the performance. With respect to the first ones, we can cite [17] for multiprocessors, [18] for GPUs, and [19] for cloud platforms. All of them showed the advantages of using parallel models for reducing the execution time when using a parallel platform.…”

Section: Related Workmentioning

confidence: 99%

A Fresh Approach to Evaluate Performance in Distributed Parallel Genetic Algorithms

Harada

Alba

Luque

2021

Preprint

View full text Add to dashboard Cite

This work proposes a novel approach to evaluate and analyze the behavior of multi-population parallel genetic algorithms (PGAs) when running on a cluster of multi-core processors. In particular, we deeply study their numerical and computational behavior by proposing a mathematical model representing the observed performance curves. In them, we discuss the emerging mathematical descriptions of PGA performance instead of, e.g., individual isolated results subject to visual inspection, for a better understanding of the effects of the number of cores used (scalability), their migration policy (the migration gap, in this paper), and the features of the solved problem (type of encoding and problem size). The conclusions based on the real figures and the numerical models fitting them represent a fresh way of understanding their speed-up, running time, and numerical effort, allowing a comparison based on a few meaningful numeric parameters. This represents a set of conclusions beyond the usual textual lessons found in past works on PGAs. It can be used as an estimation tool for the future performance of the algorithms and a way of finding out their limitations.

show abstract

“…Authors in [15][16][17][18] also presented how to use GPUs to parallelize the island model of the genetic algorithm (IMGA). They focused on proposing parallel strategies for the genetic operators that are appropriate to the studied issue, but they did not address details about the mechanism for achieving global synchronization.…”

Section: Previous Workmentioning

confidence: 99%

“…This model doesn't require global synchronization following each genetic step because each island evolves independently. Inter-block synchronization is implemented after each step [17]. The migration step is an exception and involves global synchronization between all GPU blocks to migrate some individuals from an island to a neighboring island through the global memory.…”

Section: Genetic Algorithm Over Gpumentioning

confidence: 99%

A Lightweight Island Model for the Genetic Algorithm over GPGU

Alraslan,

Hilal AlKurdi

2023

Int. j. electr. comput. eng. syst. (Online)

View full text Add to dashboard Cite

This paper presents a parallel approach of the genetic algorithm (GA) over the Graphical Processing Unit (GPU) to solve the Traveling Salesman Problem (TSP). Since the earlier studies did not focus on implementing the island model in a persistent way, this paper introduces an approach, named Lightweight Island Model (LIM), that aims to implement the concept of persistent threads in the island model of the genetic algorithm. For that, we present the implementation details to convert the traditional island model, which is separated into multiple kernels, into a computing paradigm based on a persistent kernel. Many synchronization techniques, including cooperative groups and implicit synchronization, are discussed to reduce the CPU-GPU interaction that existed in the traditional island model. A new parallelization strategy is presented for distributing the work among live threads during the selection and crossover steps. The GPU configurations that lead to the best possible performance are also determined. The introduced approach will be compared, in terms of speedup and solution quality, with the traditional island model (TIM) as well as with related works that concentrated on suggesting a lighter version of the master-slave model, including switching among kernels (SAK) and scheduled light kernel (SLK) approaches. The results show that the new approach can increase the speed-up to 27x over serial CPU, 4.5x over the traditional island model, and up to 1.5–2x over SAK and SLK approaches.

show abstract

Acceleration of Genetic Algorithm on GPU CUDA Platform

Cited by 6 publications

References 12 publications

Graphics processing unit acceleration of the island model genetic algorithm using the CUDA programming platform

Graphics processing unit acceleration of the island model genetic algorithm using the CUDA programming platform

A Fresh Approach to Evaluate Performance in Distributed Parallel Genetic Algorithms

A Lightweight Island Model for the Genetic Algorithm over GPGU

Contact Info

Product

Resources

About