Scheduling divisible loads on heterogeneous linear networks using pipelined communications

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

This work considers the divisible load distribution problem on heterogeneous linear networks. A divisible load distribution determines optimal fractions of the load and assigns them to more than one processor for minimizing the parallel execution time. Two algorithms P (pipelined communication) and M (modified method) have been proposed. The algorithm P employs the pipelined communication technique in the design. The algorithm M uses a modified method to improve the algorithm P. Closed-form expressions for the parallel processing time and speed-up are derived. In homogeneous linear networks, this work demonstrates that the pipelined communication technique outperforms the send-and-receive strategy. In heterogeneous linear networks, experiments show that the proposed algorithms are better than the send-and-receive strategy. The algorithm M is better than algorithm P when the computation-to-communication ratio is large or the number of processors is small.

Original languageEnglish
Title of host publicationIFSA-SCIS 2017 - Joint 17th World Congress of International Fuzzy Systems Association and 9th International Conference on Soft Computing and Intelligent Systems
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781509049172
DOIs
Publication statusPublished - 2017 Aug 30
Event17th Joint World Congress of International Fuzzy Systems Association and 9th International Conference on Soft Computing and Intelligent Systems, IFSA-SCIS 2017 - Otsu, Japan
Duration: 2017 Jun 272017 Jun 30

Publication series

NameIFSA-SCIS 2017 - Joint 17th World Congress of International Fuzzy Systems Association and 9th International Conference on Soft Computing and Intelligent Systems

Conference

Conference17th Joint World Congress of International Fuzzy Systems Association and 9th International Conference on Soft Computing and Intelligent Systems, IFSA-SCIS 2017
Country/TerritoryJapan
CityOtsu
Period17-06-2717-06-30

All Science Journal Classification (ASJC) codes

  • Logic
  • Computational Theory and Mathematics
  • Computer Science Applications
  • Control and Optimization
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Scheduling divisible loads on heterogeneous linear networks using pipelined communications'. Together they form a unique fingerprint.

Cite this