Skip to main navigation Skip to search Skip to main content

Optimization of parallel I/O for Cannon's algorithm based on Lustre

  • Yunchun Li*
  • , Hongda Li
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Matrix multiplication is one of the most important operations in linear algebra, widely used in many fields of science and engineering. Cannon's algorithm is a classical distributed algorithm for matrix multiplication for two-dimensional meshes. Generally, MPI-IO is used for its I/O requirements. However it has been well documented that MPI-IO performs poorly in a Lustre file system environment. As the scale of matrix multiplication increased, this problem trends to be serious, becoming one key factor impacting performance of the program. In order to improve the performance of Collective I/O of Cannon's program, we proposed a new aggregation pattern (Stripe-continuous aggregation pattern), which fully considers the stripping mechanism and lock protocol of Lustre file system. The theoretical analysis and experimental results show that the pattern can make full use of the capacity of Lustre file system compared with the other patterns, and improve the I/O performance of the Cannon's program efficiently.

Original languageEnglish
Title of host publicationProceedings - 11th International Symposium on Distributed Computing and Applications to Business, Engineering and Science, DCABES 2012
Pages31-35
Number of pages5
DOIs
StatePublished - 2012
Event11th International Symposium on Distributed Computing and Applications to Business, Engineering and Science, DCABES 2012 - Guilin, China
Duration: 19 Oct 201222 Oct 2012

Publication series

NameProceedings - 11th International Symposium on Distributed Computing and Applications to Business, Engineering and Science, DCABES 2012

Conference

Conference11th International Symposium on Distributed Computing and Applications to Business, Engineering and Science, DCABES 2012
Country/TerritoryChina
CityGuilin
Period19/10/1222/10/12

Keywords

  • Cannon's algorithm
  • Collective I/O
  • Lustre file system
  • MPI-IO
  • Parallel I/O

Fingerprint

Dive into the research topics of 'Optimization of parallel I/O for Cannon's algorithm based on Lustre'. Together they form a unique fingerprint.

Cite this