Abstract
This paper proposes a new approach to improve data-parallel languages in the context of sparse and irregular computation. We analyze the capabilities of High Performance Fortran (HPF) and Vienna Fortran, and identify a set of problems leading to sub-optimal parallel code generation for such computations on distributed-memory machines. Finally, we propose extensions to the data distribution facilities in Vienna Fortran which address these issues and provide a powerful mechanism for efficiently expressing sparse algorithms.
This work was supported by the Ministry of Education and Science (CICYT) of Spain under project TIC92-0942 and by the Austrian Science Foundation(FWF).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
R. Asenjo, L.F. Romero, M. Ujaldon and E.L. Zapata, “Sparse Block and Cyclic Data Distributions for Matrix Computation”. High Performance Computing, Technology and Applications. Eds. L. Grandinetti, G.R. Joubert, J.J. Dongarra and J. Kowalik. Elsevier Science, Amsterdam, 1995.
R. Barrett, M. Berry, T. Chan, J. Demmel, J. Donato, J. Dongarra, V. Eijkhout, R. Pozo, C. Romine and Henk van der Vorst, Templates for the solution of linear systems: Building blocks for iterative methods, SIAM 1994.
M. J. Berger and S.H. Bokhari, A Partitioning Strategy for Nonuniform Problems on Multiprocessors, IEEE Trans. Comput., vol. 36, no. 5, pp. 570–580, 1987.
A.J.C. Bik and H.A.G. Wijshoff, Compilation Techniques for Sparse Matrix Computations, ACM Int’l Conf. on Supercomputing (Tokyo), pp. 416–424, July 1993.
S.H. Bokhari, T.W. Crockett and D.M. Nicol, Parametric Binary Dissection ICASE Report No. 93–39, NASA Langley Research Center, 1993.
B. Chapman, S. Benkner, R. Blasko, P. Brezany, M. Egg, T. Fahringer, H.M. Gerndt, J. Hulman, B. Knaus, P. Kutschera, H. Moritsch, A. Schwald, V. Sipkova, H. Zima: Vienna Fortran Compilation System, User’s Guide, 1993.
B. Chapman, P. Mehrotra, and H. Zima. Programming in Vienna Fortran. Scientific Programming 1(1):31–50, Fall 1992.
R. Das, J. Saltz, K. Kennedy, P. Havlak, Index Array Flattening Through Program Transformations. Submitted to: PLDI’95.
I.S. Duff, A.M. Erisman and J.K. Reid, Direct Methods for Sparse Matrices,Clarendon Press, Oxford, 1986.
M. Eijkhout, LAPACK working note 50: Distributed sparse data structures for linear algebra operations, Tech. Report CS 92–169, Computer Science Department, University of Tennessee, Knoxville, TN, 1992.
G. Fox, S. Hiranandani, K. Kennedy, C. Koelbel, U. Kremer, C. Tseng, and M. Wu, Fortran D language specification, Dept of Computer Science Rice COMP TR90079, Rice University, 1991.
High Performance Language Specification. Version 1.0, Technical Report TR92–225, Rice University, May 3, 1993. Also available as Scientific Programming 2(1–2):1–170, Spring and Summer 1993.
P. Mehrotra and J. Van Rosendale. Programming distributed memory architectures using Kali. In A. Nicolau, D. Gelernter, T. Gross and D. Padua, editors, Advances in Languages and Compilers for Parallel Processing, pp. 364–384. Pitman/MIT-Press, 1991.
L.F. Romero and E.L. Zapata, Data distributions for sparse matrix vector multiplication solvers, J. Parallel Computing (to appear).
J. Saltz, K. Crowley, R. Mirchandaney, and H. Berryman. Run-time scheduling and execution of loops on message passing machines. Journal of Parallel and Distributed Computing, 8(2):303–312, 1990.
J. Saltz, R. Das, B. Moon, S. Sharma, Y. Hwang, R. Ponnusamy, M. Uysal, A Manual for the CHAOS Runtime Library, Computer Science Department, University of Maryland, December 22, 1993.
M. Ujaldon, E. L. Zapata, B. Chapman and H. Zima. New Data-Parallel Language Features for Sparse Matrix Computations. Proceedings of 9th International Parallel Processing Symposium. Santa Barbara, California. April, 1995 (to appear).
M. Ujaldon, E. L. Zapata, B. Chapman and H. Zima. Vienna Fortran/HPF Extensions for Sparse and Irregular Problems and its Compilation. Technical Report TR 95–4, Institute for Software Technology and Parallel Systems, University of Vienna, Austria.
M. Ujaldon and E.L. Zapata, Efficient Resolution of Sparse Indirections in Data-Parallel Compilers. Proc. 9th ACM International Conference on Supercomputing. Barcelona (Spain), July 1995.
J. Wu, R. Das, J. Saltz, H. Berryman, S. Hiranandani, Distributed Memory Compiler Design for Sparse Problems. To appear in. “IEEE Transactions on Computers”.
H. Zima, P. Brezany, B. Chapman, P. Mehrotra, A. Schwald: Vienna Fortran - A language Specification Version 1.1, University of Vienna, ACPC-TR 92–4, March 1992.
H. Zima and B. Chapman, Compiling for Distributed Memory Systems, Proceedings of the IEEE, Special Section on Languages and Compilers for Parallel Machines, pp. 264–287, February 1993. Also: Technical Report ACPC/TR 92–16, Austrian Center for Parallel Computation, November 1992.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1996 Springer Science+Business Media New York
About this chapter
Cite this chapter
Ujaldon, M., Zapata, E.L., Chapman, B.M., Zima, H.P. (1996). Data-parallel Language Features for Sparse Codes. In: Szymanski, B.K., Sinharoy, B. (eds) Languages, Compilers and Run-Time Systems for Scalable Computers. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-2315-4_19
Download citation
DOI: https://doi.org/10.1007/978-1-4615-2315-4_19
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-5979-1
Online ISBN: 978-1-4615-2315-4
eBook Packages: Springer Book Archive