Abstract
Alignment and distribution of array data should be managed by optimizing compilers for parallel computers, but current approaches to the distribution problem formulate it as an NP-complete graph optimization problem. The graphs arising in applications are large and difficult to optimize. In this paper, we improve some earlier results on methods that use graph contraction to reduce the size of a distribution problem. We report on an experiment using seven example programs that show these contraction operations to be effective in practice; we obtain from 70 to 99 percent reductions in problem size, the larger number being more typical, without loss of solution quality.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
R. Bixby, K. Kennedy, and U. Kremer, Automatic Data Layout Using 0–1 Integer Programming. Technical Report CRPC-TR93349-S, Center for Research on Parallel Computation, Rice University, Houston, Texas (November 1993).
J. M. Anderson and M. S. Lam, Global Optimizations for Parallelism and Locality on Scalable Parallel Machines. Proc. ACM SIGPLAN ’93 Conf. PLDI, Albuquerque, New Mexico, pp. 112–125 (June 1993).
S. Chatterjee, J. R. Gilbert, R. Schreiber, and T. J. Sheffler, Array Distribution in Data-Parallel Programs. In K. Pingali, U. Banerjee, D. Gelernter, A. Nicolau, and D. Padua, (eds)., Proc. of the Seventh Ann. Workshop on Languages and Compilers for Parallel Computing, Ithaca, New York, Springer-Verlag, Lecture Notes in Computer Science, 892:76–91, (August 1994). Also available as RIACS Technical Report 94.09.
J. Li and M. Chen, The Data Alignment Phase in Compiling Programs for Distributed-Memory Machines. J. of Parallel and Distrib. Comput. 13(2): 213–221 (October 1991).
S. Wholey, Automatic Data Mapping for Distributed-Memory Parallel Computers. Ph.D. Thesis, School of Computer Science, Carnegie Mellon University, Pittsburgh, Pennsylvania (May 1991). Available as Technical Report CMU-CS-91-121.
M. Gupta, Automatic Data Partitioning on Distributed Memory Multicomputers. Ph.D. Thesis, University of Illinois at Urbana-Champaign, Urbana, Illinois (September 1992). Available as Technical Reports UILU-ENG-92-2237 and CRHC-92-19.
D. J. Palermo and P. Banerjee, Automatic Selection of Dynamic Data Partitioning Schemes for Distributed-Memory Multicomputers. Talk presented at the Workshop on Automatic Data Layout and Performance Prediction. Center for Research on Parallel Computing, Rice University. (April 1995).
U. Kremer, NP-Completeness of Dynamic Remapping. Technical Report CRPC-TR93-330-S, Center for Research on Parallel Computation, Rice University, August 1993. Appears in the Proc. of the Fourth Workshop on Compilers for Parallel Computers, Delft, The Netherlands (December 1993).
S. Chatterjee, J. R. Gilbert, and R. Schreiber, Mobile and Replicated Alignment of Arrays in Data-Parallel Programs. Proc: of Supercomputing ’93, Portland, Oregon, pp. 420–429, (November 1993).
T. J. Sheffler, R. Schreiber, J. R. Gilbert, and S. Chatterjee, Aligning Parallel Arrays to Reduce Communication. Proc. of Frontiers ’95: The Fifth Symp. on the Frontiers of Massively Parallel Computation pp. 324–331 (February 1995).
S. Chatterjee, J. R. Gilbert, R. Schreiber, and T. J. Sheffler, Modeling Data-Parallel programs with the Alignment-Distribution Graph. J. Programming Languages, 2:227–258 (1994). Special issue on compiling and run-time issues for distributed address space machines.
P. Hough and T. J. Sheffler, A Performance Analysis of Collective Communication on the CM-5. Excalibur project meeting note.
J. R. Gilbert, C. Moler, and R. Schreiber, Sparse Matrices in MATLAB: Design and Implementation. SIAM J. Matrix Anal. Appl. 13(1):333–356 (January 1992).
A. V. Goldberg and R. E. Tarjan, A New Approach to the Maximum-Flow Problem. J. ACM, 35(4): 921–940 (October 1988).
Author information
Authors and Affiliations
Corresponding author
Additional information
The work was supported by the NAS Systems Division via Contract NAS 2-13721 between NASA and the Universities Space Research Association (USRA) while he was at RIACS.
Rights and permissions
About this article
Cite this article
Sheffler, T.J., Schreiber, R., Pugh, W. et al. Efficient Distribution Analysis via Graph Contraction. Int J Parallel Prog 24, 599–620 (1996). https://doi.org/10.1007/BF03356761
Published:
Issue Date:
DOI: https://doi.org/10.1007/BF03356761