Design strategies for irregularly adapting parallel applications [electronic resource].
- Washington, D.C. : United States. Department of Energy. Office of Advanced Scientific Computing Research, 2000. and Oak Ridge, Tenn. : Distributed by the Office of Scientific and Technical Information, U.S. Dept. of Energy.
- Physical Description:
- vp : digital, PDF file
- Additional Creators:
- Lawrence Berkeley National Laboratory, United States. Department of Energy. Office of Advanced Scientific Computing Research, and United States. Department of Energy. Office of Scientific and Technical Information
- Restrictions on Access:
- Free-to-read Unrestricted online access
- Achieving scalable performance for dynamic irregular applications is eminently challenging. Traditional message-passing approaches have been making steady progress towards this goal; however, they suffer from complex implementation requirements. The use of a global address space greatly simplifies the programming task, but can degrade the performance of dynamically adapting computations. In this work, we examine two major classes of adaptive applications, under five competing programming methodologies and four leading parallel architectures. Results indicate that it is possible to achieve message-passing performance using shared-memory programming techniques by carefully following the same high level strategies. Adaptive applications have computational work loads and communication patterns which change unpredictably at runtime, requiring dynamic load balancing to achieve scalable performance on parallel machines. Efficient parallel implementations of such adaptive applications are therefore a challenging task. This work examines the implementation of two typical adaptive applications, Dynamic Remeshing and N-Body, across various programming paradigms and architectural platforms. We compare several critical factors of the parallel code development, including performance, programmability, scalability, algorithmic development, and portability.
- Published through SciTech Connect., 11/01/2000., "lbnl--47804", Tenth SIAM Conference on Parallel Processing for Scientific Computing, Portsmouth, VA (US), 03/12/2000--03/14/2000., and Biswas, Rupak; Oliker, Leonid; Shan, Hongzhang; Sing, Jaswinder Pal.
- Funding Information:
- AC03-76SF00098 and 618110
View MARC record | catkey: 14347350