Compiler techniques for effective communication on distributed-memory multiprocessors

Angeles G. Navarro, Yunheung Paek, Emilio L. Zapata, David Padua

Research output: Contribution to journalConference articlepeer-review

Abstract

The Polaris restructurer transforms conventional Fortran programs into parallel form for various types of multiprocessor systems. This paper presents the results of a study on strategies to improve the effectiveness of Polaris' techniques for distributed-memory multiprocessors. Our study, which is based on the hand analysis of MDG and TRFD from the Perfect Benchmarks and TOMCATV and SWIM from SPEC benchmarks, identified three techniques that are important for improving communication optimization. Their application produces almost perfect speedups for the four programs on the Cray T3D.

Original languageEnglish (US)
Pages (from-to)74-77
Number of pages4
JournalProceedings of the International Conference on Parallel Processing
StatePublished - Jan 1 1997
Externally publishedYes
EventProceedings of the 1997 International Conference on Parallel Processing - Bloomington, IL, USA
Duration: Sep 11 1997Sep 15 1997

ASJC Scopus subject areas

  • Hardware and Architecture

Fingerprint Dive into the research topics of 'Compiler techniques for effective communication on distributed-memory multiprocessors'. Together they form a unique fingerprint.

Cite this