Run-time recognition of task parallelism within the P++ parallel array class library

Author

Parsons, Rebecca ; Quinlan, Daniel

Author_Institution

Comput. & Commun. Div., Los Alamos Nat. Lab., NM, USA

fYear

1993

fDate

6-8 Oct 1993

Firstpage

77

Lastpage

86

Abstract

This paper explores the use of a run-time system to recognize task parallelism within a C++ array class library. Run-time systems currently support data parallelism in P++, FORTRAN 90 D, and High Performance FORTRAN. But data parallelism is insufficient for many applications, including adaptive mesh refinement. Without access to both data and task parallelism such applications exhibit several orders of magnitude more message passing and poor performance. In this paper, a C++ array class library is used to implement deferred evaluation and run-time dependence for task parallelism recognition, to obtain task parallelism through a data flow interpretation of data parallel array statements. Performance results show that the analysis and optimizations are both efficient and practical, allowing us to consider more substantial optimizations

Keywords

C language; object-oriented languages; parallel languages; parallel programming; C++ array class library; FORTRAN 90 D; High Performance FORTRAN; P++ parallel array class library; data parallelism; message passing; optimizations; run-time recognition; run-time system; task parallelism; Adaptive mesh refinement; Application software; Concurrent computing; Laboratories; Message passing; Parallel processing; Performance analysis; Runtime environment; Runtime library; Software libraries;

fLanguage

English

Publisher

ieee

Conference_Titel

Scalable Parallel Libraries Conference, 1993., Proceedings of the

Conference_Location

Mississippi State, MS

Print_ISBN

0-8186-4980-1

Type

conf

DOI

10.1109/SPLC.1993.365580

Filename

365580