Processor reordering algorithms toward efficient GEN-BLOCK redistribution

Saeri Lee, Hyun Gyoo Yook, Mi Soon Koo, Myong Soon Park

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

20 Citations (Scopus)

Abstract

The use of data redistribution represents a performance tradeoff between the expected higher efficiency of a new distribution for subsequent computation and the communication cost of redistributing the data among processor memories. This paper focuses on reducing the communication cost in GEN-BLOCK redistribution using a logical processor reordering method. We propose three algorithms; Number-Oriented, Size-Oriented and Numsize-Oriented. According to experiments on CRAY T3E, the algorithms show good performance comparing typical GEN-BLOCK redistribution, which does not reorder logical processor numbers.

Original languageEnglish
Title of host publicationProceedings of the 2001 ACM Symposium on Applied Computing, SAC 2001
PublisherAssociation for Computing Machinery
Pages539-543
Number of pages5
ISBN (Print)1581132875, 9781581132878
DOIs
Publication statusPublished - 2001 Mar 1
Event2001 ACM Symposium on Applied Computing, SAC 2001 - Las Vegas, United States
Duration: 2001 Mar 112001 Mar 14

Publication series

NameProceedings of the ACM Symposium on Applied Computing

Other

Other2001 ACM Symposium on Applied Computing, SAC 2001
CountryUnited States
CityLas Vegas
Period01/3/1101/3/14

Keywords

  • Dataparallel programming
  • GEN-BLOCK
  • High performance fortran
  • Redistribution

ASJC Scopus subject areas

  • Software

Fingerprint Dive into the research topics of 'Processor reordering algorithms toward efficient GEN-BLOCK redistribution'. Together they form a unique fingerprint.

  • Cite this

    Lee, S., Yook, H. G., Koo, M. S., & Park, M. S. (2001). Processor reordering algorithms toward efficient GEN-BLOCK redistribution. In Proceedings of the 2001 ACM Symposium on Applied Computing, SAC 2001 (pp. 539-543). (Proceedings of the ACM Symposium on Applied Computing). Association for Computing Machinery. https://doi.org/10.1145/372202.372457