On the framework for parallel evolutionary computation on GPUs

• Project/Area Number: 25330296
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Soft computing
• Research Institution: Osaka Prefecture University
• Principal Investigator: Tsutsui Shigeyoshi 大阪府立大学, 理学(系)研究科(研究院), 客員研究員 (90188590)
• Project Period (FY): 2013-04-01 – 2017-03-31
• Project Status: Completed (Fiscal Year 2016)
• Budget Amount: ¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000); Fiscal Year 2015: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000); Fiscal Year 2014: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000); Fiscal Year 2013: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
• Keywords: GPU / GPGPU / 並列進化計算 / 組合せ最適化問題 / ローカルサーチ / タブーサーチ / QAP / ACO / メニコアー計算機 / SIMD / MIMD / メニーコア計算機 / メニーコアプロセッサ / 並列計算の汎用化

Outline of Final Research Achievements

Recent GPUs (Graphics Processing Units) can be applied to a general computation program and research on GPGPU (General Purpose computation on GPU) which applies GPU to various scientific computation has become popular. Evolutionary computation represented by genetic algorithm (GA) has high parallelism of processing at individual level, population level, etc, and is a suitable for parallel execution.
In this research, we developed an efficient framework for the construction of parallel evolutionary computation by GPU.

Research Products

• [Journal Article] An Introduction to Massively Parallel Computing with GPUs―V (2016)
  • Author(s): 筒井茂義
  • Journal Title: SYSTEMS, CONTROL AND INFORMATION Volume: 60 Issue: 10 Pages: 443-450
  • DOI: 10.11509/isciesci.60.10_443
  • NAID: 130006781815
  • ISSN: 0916-1600, 2424-1806
  • Open Access / Acknowledgement Compliant
• [Journal Article] Benchmarking Optimization Algorithms: An Open Source Framework for the Traveling Salesman Problem (2014)
  • Author(s): Thomas Weise, Raymond Chiong, Jorg Lassig, Ke Tang, Shigeyoshi Tsutsui, Wenxiang Chen, Zbigniew Michalewicz and Xin Yao
  • Journal Title: IEEE Computational Intelligence Magazine Volume: 9(3) Issue: 3 Pages: 40-52
  • DOI: 10.1109/mci.2014.2326101
• [Presentation] A Comparative Study for Efficient Synchronization of Parallel ACO on Multi-core Processors in Solving QAPs (2015)
  • Author(s): Shigeyoshi Tsutsui and Noriyuki Fujimoto
  • Organizer: 2015 IEEE Symposium Series on Computational Intelligence
  • Place of Presentation: Cape Town International Convention Center, Cape Town (South Africa)
  • Year and Date: 2015-12-08
  • Int'l Joint Research
• [Presentation] A Comparative Study of Synchronization of Parallel ACO on Multi-core Processor (2015)
  • Author(s): Shigeyoshi Tsutsui and Noriyuki Fujimoto
  • Organizer: Genetic and Evolutionary Computation Conference
  • Place of Presentation: Melia Castilla hotel, Madrid (Spain)
  • Year and Date: 2015-07-11
  • Int'l Joint Research
• [Presentation] The Introduction of Asymmetry on Traditional 2-Parent Crossover Operators for Crowding and Its Effects (2014)
  • Author(s): Shigeyoshi Tsutsui
  • Organizer: Simulated Evolution and Learning, 10th International Conference, SEAL 2014
  • Place of Presentation: Dunedin, New Zealand
  • Year and Date: 2014-12-15 – 2014-12-18
• [Presentation] Parallelizing Solution Construction in ACO for GPUs (2014)
  • Author(s): Noriyuki Fujimoto and Shigeyoshi Tsutsui
  • Organizer: Swarm Intelligence, 9th International Conference, ANTS 2014
  • Place of Presentation: Brussels, 1.Belgique
  • Year and Date: 2014-09-10 – 2014-09-12
• [Presentation] First results of performance comparisons on many-core processors in solving QAP with ACO: Kepler GPU versus xeon Phi (2014)
  • Author(s): Mikiko Sato, Shigeyoshi Tsutsui, Noriyuki FujimotoTsutsui, Yuji Sato and Mitaro Namiki
  • Organizer: Genetic and Evolutionary Computation Conference (GECCO) 2014 (Companion)
  • Place of Presentation: Vancouver, Canada
  • Year and Date: 2014-07-12 – 2014-07-16
• [Presentation] Parallelizing a genetic operator for GPUs (2013)
  • Author(s): Noriyuki Fujimoto and Shigeyoshi Tsutsui
  • Organizer: IEEE Congress on Evolutionary Computation (CEC 2013)
  • Place of Presentation: Cancun, Mexico
• [Presentation] A preliminary study of crowding with biased crossover (2013)
  • Author(s): Shigeyoshi Tsutsui
  • Organizer: Genetic and Evolutionary Computation Conference (GECCO) 2013 (Companion)
  • Place of Presentation: Amsterdam, The Netherlands
• [Book] 生物進化に学ぶ知的情報処理，第５章，経営と情報の深化と融合 (2014)
  • Author(s): 筒井茂義
  • Total Pages: 14
  • Publisher: 税務経理協会
• [Book] Massively Parallel Evolutionary Computaion on GPGPUs (2013)
  • Author(s): Shigeyoshi Tsutsui and Pirre Collet (Eds)
  • Total Pages: 453
  • Publisher: Springer
• [Book] An Analytical Study of Parallel GA with Independent Runs on GPUs, Chapter 6, Massively Parallel Evolutionary Computaion on GPGPUs (2013)
  • Author(s): Shigeyoshi Tsutsui and Noriyuki Fujimoto
  • Total Pages: 16
  • Publisher: Springer
• [Book] ACO with Tabu Search on GPUs for Fast Solution of the QAP, Chapter 9, Massively Parallel Evolutionary Computaion on GPGPUs (2013)
  • Author(s): Shigeyoshi Tsutsui and Noriyuki Fujimoto
  • Total Pages: 24
  • Publisher: Springer
• [Remarks] 筒井研究室
  • URL: http://www.hannan-u.ac.jp/~tsutsui/
• [Remarks] 筒井研究室
  • URL: http://www.hannan-u.ac.jp/~tsutsui/