Sage Journals: Discover world-class research

Abstract

High performance scientific applications are frequently multiphysics codes composed from single-physics programs, or have a functional decomposition based on physics as well as a domain decomposition for parallelism. In either case, dividing the application into independent components that can be developed and tested separately is useful. This requires a fast and efficient mechanism to share the large parallel data structures that are used in scientific applications. The “ M× Nproblem” is the transfer of data between two scientific parallel programs with different numbers of processes on each side. We present a solution to the M× Nproblem based on an I/O message passing interface (MPI). In this solution, the client application reads and writes data using the standard MPI I/O, but instead of going to hard drives the data are streamed in parallel between module programs working together on an integrated simulation. This approach builds on existing technology, emphasizes the easy migration of current applications, and simplifies the unit testing of the components while maintaining parallel high performance throughout the application. It also does not require a component to know how many processes another communicating component has.

Keywords

Parallel I/O multiphysics simulations software components

Get full access to this article

View all access options for this article.

References

Armstrong, R. , Gannon, D. , Geist, A. , Keahey, K. , Kohn, S. R. , McInnes, L. , Parker, S. R. , and Smolinski, B. A. 1999. Toward a common component architecture for high performance scientific computing . Proceedings of the 8th International Symposium on High Performance Distributed Computing, Redondo Beach, CA, August 3–6.

Basney, J. and Livny, M. 1999. Deploying a high throughput computing cluster. High Performance Cluster Computing. Vol. 1, Architectures and Systems, R. Buyya , editor, Prentice-Hall, Upper Saddle River, NJ , chapter 5, pp. 116–134.

Beckman, P. , Fasel, P. , Humphrey, W. , and Mniszewski, S. 1998. Efficient coupling of parallel applications using PAWS . Proceedings of the High Performance Distributed Computing Conference, Chicago, IL, July.

Carns, P. H. , Ligon, W. B. III , Ross, R. B. , and Thakur, R. 2000. PVFS: a parallel file system for Linux clusters . Proceedings of the 4th Annual Linux Showcase and Conference, Atlanta, GA, pp. 317–327 .

Dahlburg, J. et al. 2001. Fusion simulation project: integrated simulation and optimization of magnetic fusion systems . Journal of Fusion Energy 20(4): 135–196 .

Damevski, K. 2003. Parallel RMI and M-by-N data redistribution using an IDL compiler. Master's thesis, University of Utah, May.

Foster, I. , Kohr, D. Jr. , Krishnaiyer, R. , and Mogill, J. 1997. Remote I/O: fast access to distant storage . Proceedings of the 5th Workshop on Input/Output in Parallel and Distributed Systems, San Jose, CA, pp. 14–25 .

Geist, G. A. II , Kohl, J. A. , and Papadopoulos, P. M. 1997. CUMULVS: providing fault tolerance, visualization, and steering of parallel applications . International Journal of Supercomputer Applications and High Performance Computing 11(3): 224–235 .

Gropp, W. , Lusk, E. , and Thakur, R. 1999. Using MPI-2: Advanced Features of the Message Passing Interface, MIT Press, Cambridge, MA .

10.

Hutchinson, S. A. , Shadid, J. N. , and Tuminaro, R. S. 1998. Aztec Users' Guide, Version 2.0, Sandia National Laboratories, http://www.cs.sandia.gov/CRF/aztec1.html.

11.

Keahey, K. , Fasel, P. , and Mniszewski, S. 2001. PAWS: collective interactions and data transfers . Proceedings of the High Performance Distributed Computing Conference, San Francisco, CA, August.

12.

Koelbel, C. H. , Loverman, D. B. Jr. , Schreiber, R. , Steele, G. L. , and Zosel, M. E. 1994. The High Performance Fortran Handbook, MIT Press, Cambridge, MA .

13.

Maassen, J. , Kielmann, T. , and Bal, H. E. 2002. GMI: flexible and efficient group method invocation for parallel programming . Proceedings of the 6th Workshop on Languages, Compilers, and Run-time Systems for Scalable Computers, Washington, DC, March.

14.

MPI Forum . 1994. MPI: a message passing interface standard . International Journal of Supercomputer Applications and High Performance Computing 8(3/4): 159–416 .

15.

Ranganathan, M. , Acharya, A. , Edjlali, G. , Sussman, A. , and Saltz, J. 1996. A run-time coupling of data-parallel programs . Proceedings of the 1996 International Conference on Supercomputing, Philadelphia, PA, May.

16.

Szyperski, C. 1998. Component Software, Addison-Wesley, Reading, MA .

17.

Thain, D. and Livny, M. 2000. Bypass: a tool for building split execution systems . Proceedings of the 9th IEEE Symposium on High Performance Distributed Computing, Pittsburgh, PA, August 1–4, pp. 79–85 .

18.

Thain, D. and Livny, M. 2001. Multiple bypass: interposition agents for distributed computing . Journal of Cluster Computing 4: 39–47 .

19.

Thakur, R. , Gropp, W. , and Lusk, E. 1996. An abstract-device interface for implementing portable parallel-I/O interfaces . Proceedings of the 6th Symposium on the Frontiers of Massively Parallel Computation, Annapolis, MD, October, pp. 180–187 .

20.

Thakur, R., Lusk, E., and Gropp, W. 1998. Users guide for ROMIO: a high performance, portable MPI I/O implementation. Technical Memorandum ANL/MCS-TM-234, Argonne National Laboratory, July.

21.

Thakur, R. , Gropp, W. , and Lusk, E. 1999. Data sieving and collective I/O in ROMIO . Proceedings of the 7th Symposium on the Frontiers of Massively Parallel Computation, February, pp. 182–189 .

An Approach to Parallel M × N Communication

Abstract

Keywords

Get full access to this article

References