OpenMP versus MPI for PDE solvers based on regular sparse numerical operators

Future Generation Computer Systems

Volumn 22, Issue 1-2, 2006, Pages 194-203

  Nordén, Markus ^a   Holmgren, Sverker ^a   Thuné, Michael ^a  

^a UPPSALA UNIVERSITY   (Sweden)

Author keywords

Euler; MPI; NUMA; OpenMP; Optimization; PDE; Stencil; UMA

Indexed keywords

EULER; MPI; NUMA; OPENMP; PARALLEL PROGRAMMING; SPARSE CODES; STENCIL; UMA;

APPROXIMATION THEORY; COMPUTER ARCHITECTURE; DATA REDUCTION; MATHEMATICAL OPERATORS; PARALLEL PROCESSING SYSTEMS; PARTIAL DIFFERENTIAL EQUATIONS;

PROBLEM SOLVING;

EID: 26444448968     PISSN: 0167739X     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.future.2003.09.004     Document Type: Conference Paper

References (12)

1. OpenMP Architecture Review Board, OpenMP Specifications.
2. D.S. Nikolopoulos Is data distribution necessary in OpenMP? Proceedings of the SC2000, IEEE 2000
3. D.S. Nikolopoulos Scaling irregular parallel codes with minimal programming effort Proceedings of the SC2001, IEEE 2001
4. J. Bircsak Extending OpenMP for NUMA machines Proceedings of the SC2000, IEEE 2000
5. Message Passing Interface Forum, MPI Documents.
6. W.D. Gropp High-performance parallel implicit CFD Parallel Comput 27 2001 337 362
7. E. Hagersten, A. Saulsbury, and A. Landin Simple COMA node implementations Proceedings of the Hawaii International Conference on System Science 1994
8. E. Hagersten, and M. Koster WildFire: a scalable path for SMPs Proceedings of the Fifth IEEE Symposium on High-Performance Computer Architecture (HPCA) 1999
9. S. Holmgren, and D. Wallin Performance of a pseudo-spectral PDE solver on a self-optimizing NUMA architecture Proceedings of the Euro-Par 2001 Springer, Berlin 2001
10. J.D. McCalpin, Sustainable memory bandwidth in current high performance computers, Technical Report, Advanced Systems Division, Silicon Graphics, Inc., 1995.
11. L. Noordergraaf, and R. van der Pas Performance experiences on Sun's WildFire Prototype Proceedings of the SC99, IEEE 1999
12. D. Wallin, Performance of a high-accuracy PDE solver on a self-optimizing NUMA architecture, Master's Thesis, Report No. UPTEC F 01 017, Uppsala University School of Engineering, 2001.