Buffer-Safe and Cost-Driven Communication Optimization

Journal of Parallel and Distributed Computing

Volumn 57, Issue 1, 1999, Pages 33-63

  Fahringer, Thomas ^a   Mehofer, Eduard ^a  

^a UNIVERSITY OF VIENNA   (Austria)

Author keywords

Buffer safe communication optimization; Communication vectorization; Latency hiding; Message aggregation; Message coalescing; Performance prediction; Unidirectional data flow analysis

Indexed keywords

EID: 0002893498     PISSN: 07437315     EISSN: None     Source Type: Journal    
DOI: 10.1006/jpdc.1998.1512     Document Type: Article

References (31)

1. Adve V. S., Mellor-Crummey J., Anderson M., Kennedy K., Wang Jhy-Chun, Reed D, A. Integrating compilation and performance analysis for data parallel programs. Proceedings of the Workshop on Debugging and Performance Tuning for Parallel Computing Systems. 1996;IEEE Computer Society Press, Los Alamitos.
2. Amarasinghe S. P., Lam M. S. Communication optimization and code generation for distributed memory machines. Proceedings ACM SIGPLAN'93 Conference on Programming Language Design and Implementation. June 1993.
3. Banerjee P., Chandy J. A., Gupta M., Holm J. G., Lain A., Palermo D. J., Ramaswamy S., Su E. The PARADIGM compiler for distributed-memory message passing multicomputers. Proceedings of the First International Workshop on Parallel Processing. Dec. 1994;Bangalore, India. p. 322-330.
4. Benkner S., Andel S., Blasko R., Brezany P., Celic A., Chapman B., Egg M., Fahringer T., Hulman J., Hou Y., Kelc E., Mehofer E., Moritsch H., Paul M., Sanjari K., Sipkova V., Velkov B., Wender B., Zima H. P. Vienna Fortran Compilation System - Version 2.0 - User's Guide. Oct. 1995.
5. Chakrabarti S., Gupta M., Choi J.-D. Global communication analysis and optimization. ACM SIGPLAN'96 Conference on Programming Language Design and Implementation (PLDI). May 1996.
6. Fahringer T. Estimating and optimizing performance for parallel programs. IEEE Comput. 28:1995;47-56.
7. Fahringer T. Automatic Performance Prediction of Parallel Programs. 1996;Kluwer Academic, Boston.
8. Fahringer T. Compile-time estimation of communication costs for data parallel programs. J. Parallel Distrib. Comput. 39:1996;46-65.
9. 3T. Concurrency Practice Exper. 8:1996;261-282.
10. Fahringer T. Toward symbolic performance prediction of parallel programs. IEEE Proceedings of the 1996 International Parallel Processing Symposium. 1996;IEEE Computer Society Press, Los Alamitos. p. 474-478.
11. Fahringer T. Symbolic expression evaluation to support parallelizing compilers. IEEE Proceedings of the 5th Euromicro Workshop on Parallel and Distributed Processing, London, UK. 1997;IEEE Computer Society Press, Los Alamitos. p. 22-24.
12. T. Fahringer, Efficient symbolic analysis for parallelizing compilers and performance estimators, J. Supercomputing, 12, 1998, 227, 252.
13. Fahringer T., Haines M., Mehrotra P. On the utility of threads for data parallel programming. 9th ACM International Conference on Supercomputing. 1995;Assoc. Comput. Mach. New York.
14. Fahringer T., Scholz B. Symbolic evaluation for parallelizing compilers. Proceedings of the 11th ACM International Conference on Supercomputing. 1997;Assoc. Comput. Mach. New York. p. 261-268.
15. Gupta M., Banerjee P. Compile-time estimation of communication costs on multicomputers. Proceedings Sixth International Parallel Processing Symposium. Mar. 1992.
16. Gupta M., Midkiff S., Schonberg E., Seshadri V., Wang K., Shields D., Ching W.-M., Ngo T. An HPF compiler for the IBM SP2. Proceedings, Supercomputing '95. Dec. 1995.
17. Gupta M., Schonberg E., Srinivasan H. A unified framework for optimizing communication in data-parallel programs. IEEE Trans. Parallel Distrib. Syst. 7:1996;689-704.
18. Hanxleden R. V., Kennedy K. Give-N-Take - A balanced code placement framework. ACM SIGPLAN'94 Conference on Program Language Design and Implementation. June 1994.
19. Hecht M. S. Flow Analysis of Computer Programs. 1977;Elsevier/North-Holland, Amsterdam.
20. Technical Report. Oct. 1996.
21. Hiranandani S., Kennedy K., Tseng C. . Evaluating compiler optimizations for Fortran D. J. Parallel Distrib. Comput. 21:1994;27-45.
22. Kam J. B., Ullman J. D. Global data flow analysis and iterative algorithms. J. Assoc. Comput. Mach. 23:1976;158-171.
23. Kennedy K., Sethi A. A communication placement framework with unified dependence and data-flow analysis. 3rd International Conference on Hight Performance Computing. Dec. 1996.
24. Kennedy K., Sethi A. Resource-based communication placement analysis. Proceedings of the 9th Workshop on Language and Compilers for Parallel Computing. Aug. 1996.
25. Knoop J., Rüthing O., Steffen B. Lazy code motion. Proceedings of the ACM SIGPLAN '92 Conference on Programming Language Design and Implementation (PLDI'92) (San Francisco, CA). ACM SIGPLAN Notices. 27:1992;. p. 224-234.
26. Knoop J., Rüthing O., Steffen B. The power of assignment motion. ACM SIGPLAN'95 Conference on Programming Language Design and Implementation (PLDI). June 1995.
27. Knuth D. E. An empirical study of FORTRAN programs. Software Practice Exper. 1:1971;105-133.
28. Kremer U. Technical Report. Oct. 1995.
29. Li J., Chen M. Compiling global name-space parallel loops for distributed execution. IEEE Trans. Parallel Distrib. Syst. 2:1991;361-376.
30. Zima H., Bast H.-J., Gerndt M. SUPERB - A tool for semi-automatic MIMD/SIMD parallelization. Parallel Comput. 1988;1-18.
31. Zima H., Brezany P., Chapman B., Mehrotra P., Schwald A. Vienna Fortran - A Language Specification. Technical report. 1992.