Interactive loop interchanging: a facility for tuning sequential programs to parallel architectures

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

Abstract

Loop interchanging is a powerful restructuring technique proposed for detecting implicit parallelism in conventional programming languages. There are several reasons for loop interchanging, and these are the same reasons that make the technique suitable for tuning programs to parallel architectures. This article discusses a new loop interchanging implementation in which the user can select a loop using distinct parts of the Do-loop definition in a Fortran-like language to be interchanged with either the inner-most or the outer-most Do-loop of a nested loop structure. The results of loop interchanging analysis are displayed on the screen after each iteration.

Original languageEnglish
Title of host publicationSeventeenth Annu ACM Comput Sci Conf
PublisherPubl by ACM
Pages418
Number of pages1
ISBN (Print)0897912993
Publication statusPublished - 1989
EventSeventeenth Annual ACM Computer Science Conference - Louisville, KY, USA
Duration: Feb 21 1989Feb 23 1989

Other

OtherSeventeenth Annual ACM Computer Science Conference
CityLouisville, KY, USA
Period2/21/892/23/89

ASJC Scopus subject areas

  • Engineering(all)

Fingerprint Dive into the research topics of 'Interactive loop interchanging: a facility for tuning sequential programs to parallel architectures'. Together they form a unique fingerprint.

  • Cite this

    Arafeh, B. R. (1989). Interactive loop interchanging: a facility for tuning sequential programs to parallel architectures. In Seventeenth Annu ACM Comput Sci Conf (pp. 418). Publ by ACM.