High level support for divide-and-conquer parallelism

Attila Gursoy, L. V. Kale

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


The authors present a simple language based on C for expressing divide-and-conquer computations. The language consists of a few simple extensions to C. It allows for many variations in the standard divide-and-conquer paradigm. It is implemented using the Chare Kernel parallel programming system. The Chare Kernel supports dynamic creation of work with dynamic load balancing strategies and machine-independent execution. As a result, implementation of languages and systems such as that described is simplified significantly. A translator translates divide-and-conquer programs, handling details of synchronization and communication automatically. The design of the language is presented, followed by a description of its implementation, and performance results on many parallel machines, including NCUBE/two, iPSC/2, and the Sequent symmetry.

Original languageEnglish (US)
Title of host publicationProc Supercomput 91
PublisherPubl by IEEE
Number of pages10
ISBN (Print)0818621583, 9780818621581
StatePublished - 1991
Externally publishedYes
EventProceedings of Supercomputing '91 - Albuquerque, NM, USA
Duration: Nov 18 1991Nov 22 1991

Publication series

NameProc Supercomput 91


OtherProceedings of Supercomputing '91
CityAlbuquerque, NM, USA

ASJC Scopus subject areas

  • Engineering(all)


Dive into the research topics of 'High level support for divide-and-conquer parallelism'. Together they form a unique fingerprint.

Cite this