Runtime support for data parallel tasks

Author

Haines, Matthew ; Hess, Bryan ; Mehrotra, Piyush ; Van Rosendale, John ; Zima, Hans

Author_Institution

Inst. for Comput. Applications in Sci. & Eng., NASA Langley Res. Center, Hampton, VA, USA

fYear

1995

fDate

6-9 Feb 1995

Firstpage

432

Lastpage

439

Abstract

We have recently introduced Opus, a set of Fortran language extensions that provide shared data abstractions (SDAs) as a mechanism for communication and synchronization among coarse-grain data parallel tasks. In this paper, we discuss the design and implementation issues of the runtime system necessary to support SDAs, and outline the underlying requirements for such a runtime system. We explore the feasibility of this approach by implementing a prototype of the runtime system. We give preliminary results of the prototype on the Intel Paragon, outline the current status of the project, and discuss future plans

Keywords

FORTRAN; abstract data types; data structures; synchronisation; Fortran language extensions; Intel Paragon; Opus; coarse-grain data parallel tasks; communication; data parallel tasks; runtime support; shared data abstractions; synchronization; Aerospace control; Aircraft propulsion; Computer applications; Data structures; Design optimization; NASA; Parallel languages; Parallel processing; Prototypes; Runtime;

fLanguage

English

Publisher

ieee

Conference_Titel

Frontiers of Massively Parallel Computation, 1995. Proceedings. Frontiers '95., Fifth Symposium on the

Conference_Location

McLean, VA

Print_ISBN

0-8186-6965-9

Type

conf

DOI

10.1109/FMPC.1995.380482

Filename

380482