Recent developments in I/O systems on scalable parallel computers have sparked renewed interest in out-of-core methods for computational chemistry. These methods can improve execution time significantly relative to direct methods, which perform many redundant computations. However, the widespread use of such out-of-core methods requires efficient and portable implementations of often complex I/O patterns. The ChemlO project has addressed this problem by defining an I/O interface that captures the I/O patterns found in important computational chemistry applications and by providing high performance imple mentations of this interface on multiple platforms. This development broadens the user community for parallel I/O techniques and provides new insights into the functionality required in general purpose scalable I/O libraries and the techniques required to achieve high performance I/O on scalable parallel computers.
Get full access to this article
View all access options for this article.
References
1.
Almlöf, J., Faegri, J.K., and Korsell, K.1982. Principles for a direct SCF approach to LCAO-MO ab initio calculationsJ. Comput. Chem.3:385-399.
2.
Almlöf, J., and Taylor, P.R.1984. Computational aspects of direct SCF and MCSCF methods In Advanced theories and computational approaches to the electronic structure of molecules, edited by C. E. Dykstra. Dordrecht: Reidel, pp. 107-125.
3.
Bemholdt, D.E., Apra, E., Früchtl, H.A., Guest, M.F., Harrison, R.J., Kendall, R.A., Kutteh, R.A., Long, X., Nicholas, J.B., Nichols, J.A., Taylor, H.L., Fann, G.I., Littlefield, R.J., and Nieplocha, J.1995. Parallel computational chemistry made easier: The development of NWChemInt. J. Quantum Chem. Symp . 29:475.
4.
Bernholdt, D.E., and Harrison. R.J.1996. Large-scale correlated electronic structure calculations: The RI-MP2 method on parallel computersChem. Phys. Lett.250:477.
5.
Chen, Y., Foster, I., Nieplocha, J., and Winslett, M.1997. Optimizing collective I/O performance on parallel computers: A multisystem study. In Proceedings of the 11th ACM International Conference on SupercomputingACM Press.
6.
Corbett, P., and Feitelson, D.1994. Design and implementation of the Vesta parallel file system. In Proceedings of the Scalable High-Performance Computing ConferenceLos Alamitos, CA: IEEE Computer Society Press, pp. 63-70.
7.
Corbett, P., Feitelson, D., Hsu, Y., Prost, J.-P., Snir, M., Fineberg, S., Nitzberg, B., Traversat, B., and Wong, P.1995. MPI-IO: A parallel file I/O interface for MPI, version 0.3 Technical Report NAS-95-002, NAS, NASA Ames Research Center, January.
8.
Dachsel, H., Lischka, H., Shepard, R., Nieplocha, J., and Harrison, R.J.1997. A massively parallel multireference configuration interaction program—The parallel COLUMBUS programJ. Chem. Phys.18:430.
9.
D'Azevedo, E.F., and Romine, C.1994. DONIO: Distributed object network I/O library Report ORNL/TM-12743, Oak Ridge National Laboratory .
10.
Dupuis, M., and King, H.F.1978. Molecular symmetry: Gradient of electronic energy with respect to nuclear coordinatesJ. Chem. Phys.69(9):3998-4004.
11.
Foster, I., Kesselman, C., and Tuecke, S.1996. The Nexus approach to integrating multithreading and communicationJ. Parallel and Distributed Computing37:70-82.
12.
Früchtl, H.A., Kendall, R.A., Harrison, R.J., and Dyall, K.G.1997. A parallel implementation of RI-SCF on parallel computersInt. J. Quantum Chem.64(1):63-69.
13.
Guest, M.F., Kendall, R.A., Nichols, J.A., Dunning, J.T.H., and Gordon, E.M.S.1995. Challenges of high performance computing in chemistry Technical Report PNL-10202, Pacific Northwest National Laboratory, March. Available from the National Technical Information Service, U.S. Department of Commerce, 5285 Port Royal Road, Springfield, VA 22161 U.S.A.
14.
Harrison, R.J., and Shepard, R.L.1994. Ab initio molecular electronic structure on parallel computersAnn. Rev Phys. Chem.45:623-658.
15.
Häser, M., and Ahlrichs, R.1989. Improvements of the direct SCF methodJ. Comput. Chem.10:104-111.
16.
Kendall, R.A., and Guest, M.F.1995. Input and output in chemistry applications In Grand Challenges in Computer Simulation, High Performance Computing 1995, Proceedings of the 1995 Simulation Multiconference, edited by A. M. Tentner. Society for Computer Simulation, pp. 522-526.
17.
Kendall, R.A., and Harrison, R.J.1991. A parallel version of ARGOS: A distributed memory model for shared memory Unix computersTheoretica Chimica Acta79:337-347.
18.
Miller, C., Payne, D., Phung, T., Siegel, H., and Williams, R.1995. Parallel processing of spaceborne imaging radar data In Proceedings of Supercomputing '95. ACM Press.
19.
Nieplocha, J., and Foster, I.1996. Disk resident arrays: An array-oriented library for out-of-core computations. In Proceedings of Frontiers of Massively Parallel ComputationLos Alamitos, CA: IEEE Computer Society Press, pp. 196-204.
20.
Nieplocha, J., Harrison, R.J., and Littlefield, R.J.1994. Global Arrays: A portable "shared-memory" programming model for distributed memory computers. In Proceedings of Supercomputing 1994Los Alamitos, CA: IEEE Computer Society Press, pp. 340-349.
21.
Nieplocha, J., Harrison, R.J., and Littlefield, R.J.1996. Global Arrays: A nonuniform memory access programming model for high-performance computersJ. Supercomputing10:169-189.
22.
Seamons, K.E., Chen, Y., Jones, P., Jozwiak, J., and Winslett, M.1995. Server-directed collective I/O in Panda. In Pro ceedings of Supercomputing '95. Los Alamitos, CA : IEEE Computer Society Press.
23.
Shepard, R.1993. Elimination of the diagonalization bottleneck in parallel direct-SCF methodsTheoretica Chimica Acta84:343.
24.
Szabo, A., and Ostlund, N.S.1989. Modem quantum chemistryNew York: McGraw-Hill.
25.
Taylor, P.R.1987. Integral processing in beyond-Hartree-Fock calculationsInt. J. Quantum Chem.31:521-534.
26.
Thakur, R., Bordawekar, R., Choudhary, A., Ponnusamy, R., and Singh, T.1994. PASSION runtime library for parallel I/O In Proceedings of the Scalable Parallel Libraries Conference. Los Alamitos, CA: IEEE Computer Society Press, pp. 119-128.
27.
Thakur, R., Gropp, W., and Lusk, E.1996. An experimental evaluation of the parallel I/O systems of the IBM SP and Intel Paragon using a production application. In Proceedings of the 3rd Intemational Conference of the Austrian Center for Parallel Computation (ACPC) (with special emphasis on parallel databases and parallel I/O). Lecture Notes in Computer Science 1127. Springer-Verlag, 24-35.
28.
Vahtras, O., Almlöf, J., and Feyereisen, M.W.1993. Integral approximations for LCAO-SCF calculationsChem. Phys. Lett.213(5-6):514.
29.
Wong, A.T., and Harrison, R.J.1995. Approaches to large-scale parallel self-consistent field calculationsJ. Comput. Chem.16:1291.
