Extracting synchronization-free slices of operations in perfectly-nested loops
Pages 244 - 249
Abstract
Extracting synchronization-free slices in loops is of great importance for parallel and distributed computing, it allows for code locality enhancement and relaxation of memory requirements. We present a novel approach for extracting synchronization-free slices made up of operations of a perfectly nested loop. It can be applied to both uniform and non-uniform loops. Our approach, based on operations on relations and sets, requires exact dependence analysis. Results of experiments are presented.
References
[1]
Allen, R, Kennedy, K. Optimizing Compilers for Modern Architectures . Morgan Kaufmann. (2001)
[2]
Amarasinghe S. P., Lam M. S. Communication optimization and code generation for distributed memory machines. In Proceedings of the SIGPLAN'93 , pp. 126--138. (1993)
[3]
Banerjee U. Unimodular transformations of double loops. In Proceedings of the Third Workshop on Languages and Compilers for Parallel Computing , pp. 192--219. (1990)
[4]
Feautrier P. Toward automatic distribution. Journal of Parallel Processing Letters 4 , pp. 233--244. (1994).
[5]
Lim W., Lam M. S. Communication-free parallelization via affine transformations. In Proc. of the 7th Workshop on languages and compilers for parallel computing , pp. 92--106. (1994).
[6]
Lim W., Lam M. S. Maximizing parallelism and minimizing synchronization with affine transforms. In Conference record of the 24 th annual ACS symposium on principles of programming languages . (1997).
[7]
Wolf M. E. Improving locality and parallelism in nested loops . Ph.D. Dissertation CSL-TR-92-538, Stanford University, Dept. Computer Science. (1992).
[8]
Pugh W., Rosser E. Iteration Space Slicing and Its Application to Communication Optimization In Proc. of the Intern. Conference on Supercomputing , pp 221--228. (1997).
[9]
Pugh W., Wonnacott D. Constraint-based array dependence analysis. In ACM Trans. on Programming Languages and Systems . (1998).
[10]
Beletska A., Bielecki W., San Pietro P. Extracting Coarse-Grained Parallelism in Program Loops with the Slicing Framwork. In Proceedings of ISPDC '07. (2007)
[11]
Kelly W., Pugh W., Rosser E. and Shpeisman T. Transitive Closure of Infinite Graphs and its Applications. Intern. Journal of Parallel Programming , v. 24, n. 6, pp. 579--598. (1996).
[12]
Kelly W., Pugh W. Minimizing communication while preserving parallelism. In Proc. of the 1996 ACM International Conference on Supercomputing , pp. 52--60. (1996).
[13]
Ouillere F., Rajopadhye S., Wilde D. Generation of efficient nested loops from polyhedra. International Journal of Parallel Programming 28 . (2000).
[14]
Vasilache N., Bastoul C., and Cohen A. Polyhedral code generation in the real world. In Proceedings of the International Conference on Compiler Construction (ETAPS CC'06) , LNCS, pp 185--201, Vienna, Austria. Springer-Verlag. (2006).
[15]
Netlib Repository at UTK and ORNL, http://www.netlib.org/benchmark/livermorec.
[16]
Bastoul C., Cohen A., Girbal S., Sharma S., and Temam O. Putting polyhedral loop transformations to work. In Languages and Compilers for Parallel Computing (LCPC'03) . LNCS, pp 23--30, College Station, Texas. Springer-Verlag. (2003).
[17]
Cohen A., Girbal S., and Temam O. A polyhedral approach to ease the composition of program transformations. In Euro-Par'04 . LNCS 3149, pp. 292--303, Pisa, Italy. Springer-Verlag. (2004).
[18]
Darte A., Robert Y., Vivien F. Scheduling and Automatic Parallelization . Birkhäuser Boston. (2000)
[19]
Feautrier P. Some efficient solutions to the affine scheduling problem, part i, one dimensional time. International Journal of Parallel Programming 21 , pp. 313--348. (1992).
[20]
Feautrier P. Some efficient solutions to the affine scheduling problem, part ii, multidimensional time. Intern. Journal of Parallel Programming 21 , pp. 389--420, (1992).
- Extracting synchronization-free slices of operations in perfectly-nested loops
Recommendations
Finding Synchronization-Free Slices of Operations in Arbitrarily Nested Loops
ICCSA '08: Proceedings of the international conference on Computational Science and Its Applications, Part IIThis paper presents a new approach for extracting synchronization-free parallelism being represented by dependent statement instances of an arbitrarily nested loop. Presented algorithms can be applied to both uniform and non-uniform loops. The main ...
Extracting synchronization-free threads in perfectly nested loops using the omega project software
SEPADS'05: Proceedings of the 4th WSEAS International Conference on Software Engineering, Parallel & Distributed SystemsAlgorithms, permitting us to find synchronization-free threads comprised of iterations of perfectly nested uniform and non-uniform loops, are presented. They require an exact representation of loop-carried dependences. To describe and implement the ...
Transformations techniques for extracting parallelism in non-uniform nested loops
Executing a program in parallel machines needs not only to find sufficient parallelism in a program, but it is also important that we minimize the synchronization and communication overheads in the parallelized program. This yields to improve the ...
Comments
Information & Contributors
Information
Published In
Publisher
ACTA Press
United States
Publication History
Published: 06 November 2007
Author Tags
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 12 Feb 2025