Parallel Genetic Algorithms on Multiple FPGAs

Author:

Guo Liucheng1,Funie Andreea Ingrid1,Thomas David B.1,Fu Haohuan2,Luk Wayne1

Affiliation:

1. Imperial College London, London, UK

2. Tsinghua University, Beijing, P.R. China

Abstract

Genetic algorithms (GA) have been shown to be effective in the optimization of many large-scale real-world problems in a reasonable amount of time. Parallel GAs not only reduce the overall GA execution time, but also bring higher quality solutions due to parallel search in multiple parts of the solution space. This paper proposes a parallel GA system on hardware such as Field-Programmable-Gate-Arrays (FPGAs). Our approach targets multiple FPGAs by exploring different search areas of the same solution space with different behaviours. Each FPGA contains an optimised customisable GA which can be configured using run-time parameters, removing the need for expensive recompilation. This paper also explores adjustment of the migration gap, providing empirical guidance on good settings to users. Experiments on three problems show the high performance of our system, with a 30 times speedup achieved compared to a multi-core CPU-based implementation.

Publisher

Association for Computing Machinery (ACM)

Reference21 articles.

1. M. Mitchell "An Introduction to Genetic Algorithms" Bradford Book 1998. M. Mitchell "An Introduction to Genetic Algorithms" Bradford Book 1998.

2. HGA

3. Development of a flexible hardware core for genetic algorithm;Pimery J.;Intelligent Computing and Intelligent Systems,2009

Cited by 11 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. GSGP-hardware: instantaneous symbolic regression with an FPGA implementation of geometric semantic genetic programming;Genetic Programming and Evolvable Machines;2024-06-25

2. A novel partition strategy for efficient implementation of 3D Cellular Genetic Algorithms;Microprocessors and Microsystems;2024-02

3. FPGA Accelerated Parallel HsClone GA for Digital Circuit Configuration in CGP Format;Journal of The Institution of Engineers (India): Series B;2023-09-21

4. Multiprogram tools for FPGA boards with single identifier on Windows;2023 19th International Conference on Synthesis, Modeling, Analysis and Simulation Methods and Applications to Circuit Design (SMACD);2023-07-03

5. Memristor Parallel Computing for a Matrix-Friendly Genetic Algorithm;IEEE Transactions on Evolutionary Computation;2022-10

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3