This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Optimal Tree Access by Elementary and Composite Templates in Parallel Memory Systems
April 2002 (vol. 13 no. 4)
pp. 399-412

In this paper, we study efficient strategies for mapping onto parallel memory systems complete trees that are accessed by fixed templates (like complete subtrees, paths, or any combinations their of). These mappings are evaluated with respect to the following criteria: 1) the largest number of data items that can be accessed in parallel without memory conflicts; 2) the number of memory conflicts that can occur when accessing templates of size equal to the number of available memory modules, thereby exploiting the full parallelism of the system; 3) the complexity of the memory addressing scheme, i.e., the cost of retrieving the module where a given data item is mapped. We show that there exist trade-offs between these three criteria and the performance of different mapping strategies depends on the emphasis given on each of these criteria. More specifically, we describe an algorithm for mapping complete binary trees of height H onto M memory modules and prove that it achieves the following performance results: 1) conflict-free access to complete subtrees of size K and paths of size N such that N+K-\lceil\log K\rceil \leq M; 2) at most 1 conflict in accessing complete subtrees and paths of size M; 3) O\left({K\over M} + c\right) conflicts when accessing a composite template of K nodes consisting of c disjoint subsets, each subset being a complete subtree, or a path or a set of consecutive nodes in a level of the tree. Furthermore, we show that an existing mapping algorithm results in a larger number, namely O\left({K\over{\sqrt{M\log M}}} + c\right), of conflicts when accessing a composite template. However, such an algorithm maps each single node in O(1) time, while the new algorithm requires O(H/N-\log K) time.

[1] V. Auletta, S.K. Das, A. De Vivo, M.C. Pinotti, and V. Scarano, “Towards a Universal Mapping Algorithms for Accessing Trees in Parallel Memory Systems,” Proc. Int'l Parallel Processing Symp. (IPPS/SPDP), pp. 447-459, Apr. 1998.
[2] V. Auletta, S.K. Das, M.C. Pinotti, and V. Scarano, “Optimal Tree Access by Elementary and Composite Templates in Parallel Memory Systems,” Proc. Int'l Parallel and Distributed Processing Symp. (IPDPS), Apr. 2001.
[3] V. Auletta, A. De Vivo, and V. Scarano, “Multiple Template Access of Trees in Parallel Memory Systems,” J. Parallel and Distributed Computing, vol. 49, np. 1, pp. 22-39, Feb. 1998.
[4] C.J. Colbourn and K. Heirich, "Conflict-Free Access to Parallel Memories," J. Parallel and Distributed Computing, vol. 14, pp. 193-200, 1992.
[5] T.H. Cormen,C.E. Leiserson, and R.L. Rivest,Introduction to Algorithms.Cambridge, Mass.: MIT Press/McGraw-Hill, 1990.
[6] R. Creutzburg and L. Andrews, “Recent Results on the Parallel Access to Tree-Like Data Structures—The Isotropic Approach,” Proc. of Int'l Conf. Parallel Processing, vol. 1, pp. 369-372, 1991.
[7] S.K. Das and M.C. Pinotti, “Conflict-Free Template Access ink-Ary and Binomial Trees,” Proc. 11th ACM Int'l Conf. Supercomputing, pp. 237-244, July 1997.
[8] S.K. Das and M.C. Pinotti, “Load Balanced Mapping of Data Structures in Parallel Memory Modules for Fast and Conflict-Free Templates Access,” Proc. Fifth Int'l Workshop Algorithms and Data Structures, vol. 1272, pp. 272-281, Aug. 1997.
[9] S.K. Das and M.C. Pinotti, “Optimal Mappings ofq-Ary and Binomial Trees into Parallel Memory Modules for Fast and Conflict-Free Access to Path and Subtree Templates,” J. Parallel and Distributed Computing, vol. 60, no. 8, pp. 998-1027, 2000.
[10] S.K. Das, M.C. Pinotti, and F. Sarkar, “Optimal and Load Balanced Mapping of Parallel Priority Queues in Hypercubes,” IEEE Trans. Parallel and Distributed Systems, vol. 7, no. 6, pp. 555-564, June 1996.
[11] S.K. Das and F. Sarkar, “Conflict-Free Data Access of Arrays and Trees in Parallel Memory Systems,” Proc. Sixth IEEE Symp. Parallel and Distributed Processing, pp. 377-383, 1994.
[12] S.K. Das, F. Sarkar, and M.C. Pinotti, “Conflict-free Path Access of Trees in Parallel Memory Systems with Application to Distributed Heap Implementation,” Proc. 24th Int'l Conf. Parallel Processing, vol. III, pp. 164-167, 1995.
[13] J. J'aJ'a, An Introduction to Parallel Algorithms.New York: Addison-Wesley, 1992.
[14] F.T. Leighton,Introduction to Parallel Algorithms and Architectures: Arrays, Trees, Hypercubes.San Mateo, Calif.: Morgan Kaufmann, 1992.
[15] M.C. Pinotti and G. Pucci, "Parallel Algorithms for Priority Queue Operations," Theoretical Computer Science, vol. 148, no. 1, pp. 171-180, 1995.
[16] D. Kaznachey, A. Jagota, and S. K. Das, “Primal-Target Neural Net Heuristics for the Hypergraph k-Coloring Problem,” Proc. Int'l Conf. Neural Networks (ICNN '97), pp. 1251-1255, June 1997.
[17] K. Kim and V.K. Prasanna, “Latin Squares for Parallel Array Access,” IEEE Trans. Parallel and Distributed Systems, vol. 4, no. 4, pp. 361-370, Apr. 1993.
[18] H.A.G. Wijshoff, “Storing Trees into Parallel Memories,” Parallel Computing, pp. 253-261, 1986.

Index Terms:
complete trees, composite templates, conflict-free access, elementary templates, mapping scheme, parallel memory system
Citation:
Vincenzo Auletta, Sajal K. Das, Amelia De Vivo, M. Cristina Pinotti, Vittorio Scarano, "Optimal Tree Access by Elementary and Composite Templates in Parallel Memory Systems," IEEE Transactions on Parallel and Distributed Systems, vol. 13, no. 4, pp. 399-412, April 2002, doi:10.1109/71.995820
Usage of this product signifies your acceptance of the Terms of Use.