DocumentCode :
2256790
Title :
Tools-supported HPF and MPI parallelization of the NAS parallel benchmarks
Author :
Clémençon, Christian ; Decker, Karsten M. ; Deshpande, Vaibhav R. ; Endo, Akiyoshi ; Fritscher, Josef ; Lorenzo, Paulo A R ; Masuda, Norio ; Müller, Andreas ; Rühl, Roland ; Sawyer, William ; Wylie, Brian J N ; Zimmermann, Frank
Author_Institution :
Centro Svizzero di Calcolo Sci., Manno, Switzerland
fYear :
1996
fDate :
27-31 Oct. 1996
Firstpage :
309
Lastpage :
318
Abstract :
High Performance Fortran (HPF) compilers and communication libraries with the standardized Message Passing Interface (MPI) are becoming widely available, easing the development of portable parallel applications. The Annai tool environment supports programming, debugging and tuning of both HPF- and MPI-based applications. Considering code development time to be as important as final performance, we address how sequential versions of the familiar NAS parallel benchmark kernels can be expediently parallelized with appropriate tool support. While automatic parallelization of scientific applications written in traditional sequential languages remains largely impractical, Annai provides users with high-level language extensions and integrated program engineering support tools. Respectable performance and scalability in most cases are obtained with this straightforward parallelization strategy on the NEC Cenju-3 distributed-memory parallel processor even without recourse to platform-specific optimizations or major program transformations.
Keywords :
parallel languages; Annai tool; High Performance Fortran; Message Passing Interface; NAS parallel benchmarks; NEC Cenju-3 distributed-memory parallel processor; code development time; communication libraries; compilers; high-level language; parallel benchmark kernels; parallel programming; performance; portable parallel applications; program debugging; scalability; scientific applications; sequential languages; Application software; Concurrent computing; Distributed computing; Kernel; Libraries; Message passing; National electric code; Optimizing compilers; Parallel programming; Supercomputers;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Frontiers of Massively Parallel Computing, 1996. Proceedings Frontiers '96., Sixth Symposium on the
Conference_Location :
Annapolis, MA, USA
ISSN :
1088-4955
Print_ISBN :
0-8186-7551-9
Type :
conf
DOI :
10.1109/FMPC.1996.558106
Filename :
558106
Link To Document :
بازگشت