Extending Vienna Fortran with task parallelism

Barbara Chapman; Piyush Mehrotra; John Van Rosendale; Hans Zima

Extending Vienna Fortran with task parallelism

Barbara Chapman
, Piyush Mehrotra
, John Van Rosendale
, Hans Zima

Computer Science

University of Vienna

Research output: Contribution to conference › Paper › peer-review

1 Scopus citations

Abstract

Vienna Fortran supports a wide range of data-parallel numerical problems. However, a significant number of scientific and engineering applications are of a multi-disciplinary and heterogeneous nature and thus do not fit well into the data parallel paradigm. In this paper we present new language extensions to fill this gap. Tasks can be spawned as asynchronous activities in a homogeneous or heterogeneous computing environment; they interact by sharing access to Shared Data Abstractions (SDAs). SDAs are an extension of Fortran 90 modules, representing a pool of common data, together with a set of methods for controlled access to these data and a mechanism for providing persistent storage. These extensions support the integration of data and task parallelism and can be used to express task parallel applications in a natural and efficient way.

Original language	English
Pages	258-263
Number of pages	6
State	Published - 1994
Event	Proceedings of the 1994 International Conference on Parallel and Distributed Systems - Hsinchu, China Duration: Dec 19 1994 → Dec 21 1994

Conference

Conference	Proceedings of the 1994 International Conference on Parallel and Distributed Systems
City	Hsinchu, China
Period	12/19/94 → 12/21/94

Cite this

@conference{f6ae11a32fdf40d9be4241be7b3481c2,

title = "Extending Vienna Fortran with task parallelism",

abstract = "Vienna Fortran supports a wide range of data-parallel numerical problems. However, a significant number of scientific and engineering applications are of a multi-disciplinary and heterogeneous nature and thus do not fit well into the data parallel paradigm. In this paper we present new language extensions to fill this gap. Tasks can be spawned as asynchronous activities in a homogeneous or heterogeneous computing environment; they interact by sharing access to Shared Data Abstractions (SDAs). SDAs are an extension of Fortran 90 modules, representing a pool of common data, together with a set of methods for controlled access to these data and a mechanism for providing persistent storage. These extensions support the integration of data and task parallelism and can be used to express task parallel applications in a natural and efficient way.",

author = "Barbara Chapman and Piyush Mehrotra and \{Van Rosendale\}, John and Hans Zima",

year = "1994",

language = "English",

pages = "258--263",

note = "Proceedings of the 1994 International Conference on Parallel and Distributed Systems ; Conference date: 19-12-1994 Through 21-12-1994",

}

TY - CONF

T1 - Extending Vienna Fortran with task parallelism

AU - Chapman, Barbara

AU - Mehrotra, Piyush

AU - Van Rosendale, John

AU - Zima, Hans

PY - 1994

Y1 - 1994

N2 - Vienna Fortran supports a wide range of data-parallel numerical problems. However, a significant number of scientific and engineering applications are of a multi-disciplinary and heterogeneous nature and thus do not fit well into the data parallel paradigm. In this paper we present new language extensions to fill this gap. Tasks can be spawned as asynchronous activities in a homogeneous or heterogeneous computing environment; they interact by sharing access to Shared Data Abstractions (SDAs). SDAs are an extension of Fortran 90 modules, representing a pool of common data, together with a set of methods for controlled access to these data and a mechanism for providing persistent storage. These extensions support the integration of data and task parallelism and can be used to express task parallel applications in a natural and efficient way.

AB - Vienna Fortran supports a wide range of data-parallel numerical problems. However, a significant number of scientific and engineering applications are of a multi-disciplinary and heterogeneous nature and thus do not fit well into the data parallel paradigm. In this paper we present new language extensions to fill this gap. Tasks can be spawned as asynchronous activities in a homogeneous or heterogeneous computing environment; they interact by sharing access to Shared Data Abstractions (SDAs). SDAs are an extension of Fortran 90 modules, representing a pool of common data, together with a set of methods for controlled access to these data and a mechanism for providing persistent storage. These extensions support the integration of data and task parallelism and can be used to express task parallel applications in a natural and efficient way.

UR - https://www.scopus.com/pages/publications/0028748773

M3 - Paper

AN - SCOPUS:0028748773

SP - 258

EP - 263

T2 - Proceedings of the 1994 International Conference on Parallel and Distributed Systems

Y2 - 19 December 1994 through 21 December 1994

ER -

Extending Vienna Fortran with task parallelism

Abstract

Conference

Other files and links

Fingerprint

Cite this