Abstractions for parallel N-body simulations

Author

Bhatt, Sandeep ; Chen, Marina ; Lin, Cheng-Yee ; Liu, Pangfeng

Author_Institution

Dept. of Comput. Sci., Yale Univ., New Haven, CT, USA

fYear

1992

fDate

26-29 Apr 1992

Firstpage

38

Lastpage

45

Abstract

Introduces C++ programming abstractions for maintaining load-balanced partitions of irregular and adaptive trees. Such abstractions are useful across a range of applications and MIMD architectures. The use of these abstractions is illustrated for gravitational N-body simulation. The strategy for parallel N-body simulation is based on a technique for implicitly representing a global tree across multiple processors. This substantially reduces the programming complexity and the overhead for distributed memory architectures. The overhead is further reduced by maintaining incremental data structures

Keywords

C language; astronomy computing; astrophysics computing; celestial mechanics; data structures; digital simulation; distributed memory systems; object-oriented languages; parallel programming; resource allocation; stellar dynamics; C++ programming abstractions; MIMD architectures; adaptive trees; astrophysics; celestial mechanics; distributed memory architectures; global tree; gravitational N-body simulation; incremental data structures; irregular trees; load-balanced partitions; parallel N-body simulations; programming complexity; stellar dynamics; Application software; Computational modeling; Computer science; Computer simulation; Large-scale systems; Load management; Memory architecture; Object oriented modeling; Parallel programming; Plasma simulation;

fLanguage

English

Publisher

ieee

Conference_Titel

Scalable High Performance Computing Conference, 1992. SHPCC-92, Proceedings.

Conference_Location

Williamsburg, VA

Print_ISBN

0-8186-2775-1

Type

conf

DOI

10.1109/SHPCC.1992.232690

Filename

232690