This Article 
 Bibliographic References 
 Add to: 
Join and Data Redistribution Algorithms for Hypercubes
February 1993 (vol. 5 no. 1)
pp. 161-168

An important aspect of database processing in parallel computer systems is the use of data parallel algorithms. Several parallel algorithms for the relational database join operation in a hypercube multicomputer system are given. The join algorithms are classified as cycling or global partitioning based on the tuple distribution method employed. The various algorithms are compared under a common framework, using time complexity analysis as well as an implementation on a 64-node NCUBE hypercube system. In general, the global partitioning algorithms demonstrate better speedup. However, the cycling algorithm can perform better than the global algorithms in specific situations, viz., when the difference in input relation cardinalities is large and the hypercube dimension is small. The usefulness of the data redistribution operation in improving the performance of the join algorithms, in the presence of uneven data partitions, is examined. The results indicate that redistribution significantly decreases the join algorithm execution times for unbalanced partitions.

[1] C. K. Baru and O. Frieder, "Database operations in a cube-connected multicomputer system,"IEEE Trans. Comput., vol. C-38, pp. 920-927, June 1989.
[2] H. Boralet al., "Prototyping Bubba, A highly parallel database system,"IEEE Trans Knowl. Data Eng., vol. 2, pp. 4-24, Mar. 1990.
[3] K. Bratbergsengen and T. Gjelsvik, "The Development of the CROSS8 and HC16-186 (database) computers," inProc. Sixth Int. Workshop on Database Machines, Deauville, France, June 1989, pp. 359-372.
[4] W. J. Dally,A VLSI Architecture for Concurrent Data Structures. Boston, MA: Kluwer Academic, 1987, pp. 144-161.
[5] D. Dewitt et al., "The Gamma database machine project,"IEEE Trans. Knowl. Data Eng., vol. 2, pp. 44-62, Mar. 1990.
[6] O. Frieder, "Multiprocessor algorithms for relational database operators on hypercube systems,"Comput., vol. 23, no. 11, pp. 13-28, Nov. 1990.
[7] C.-T. Ho and M. Raghunath, "Efficient communication primitives on circuit-switched hypercubes," inProc. 6th Distributed Memory Computing Conf., 1991, pp. 390-397.
[8] S. Johnsson and C. Ho, "Optimum broadcasting and personalized communication in hypercubes,"IEEE Trans. Comput., vol. C-38, pp. 1249-1269, Sept. 1989.
[9] M. Lakshmi and P. Yu, "Effectiveness of parallel joins,"IEEE Trans. Knowl. Data Eng., vol. 2, pp. 410-424, Dec. 1990.
[10] S. F. Nugent, "The iPSC/2 Direct-Connect communications technology," inProc. Third Conf. Hypercube Comput. Appl., Pasadena, CA, Jan. 1988, pp. 56-60.
[11] E. R. Omiecinski and E. Tien Lin, "Hash-based and index-based join algorithms for cube and ring connected multicomputers,"IEEE Trans. Knowl. Data Eng., vol. 1, pp. 329-343, Sept. 1989.
[12] R. P. Pargas, J. C. Peck, and A. L. Pugh, "Use of a semi-join program for join queries on a hypercube," inProc 4th Conf. on Hypercubes, Concurrent Computers, and Applications, Monterey, CA, Mar. 1989.
[13] D. Schneider and D. Dewitt, "A performance evaluation of four parallel join algorithms in a shared-nothing multiprocessor environment," inProc. ACM SIGMOD Conf.(Portland, OR), May-June 1989, p. 110.
[14] S. Seidel, M.-H. Lee, and S. Fotedar, "Concurrent bidirectional communication on the Intel iPSC/860 and iPSC/2," inProc. 6th Distributed Memory Computing Conf., 1991, pp. 283-286.
[15] S. R. Seidel, "Circuit-switched vs. store-and-forward solutions to symmetric communication problems," inProc. 4th Conf. on Hypercubes, Concurrent Computers, and Applications, Mar. 1989, pp. 253-255.
[16] C. L. Seitz, "The Cosmic Cube,"Commun. ACM, pp. 22-33, Jan. 1985.
[17] H. Sulivan and T. R. Bashkov, "A large scale homogeneous, fully distributed parallel machine, I," inProc. 4th Symp. Comput. Arch., March 1977, pp. 105-117.
[18] A. Tanenbaum,Computer Networks. Englewood Cliffs, NJ: Prentice-Hall, 1988.
[19] E. Upchurchet al., "Parallel joins on the MARK III hypercube," inProc 4th Conf. on Hypercubes, Concurrent Computers, and Applications, Monterey, CA, Mar. 1989.
[20] P. Valduriez and G. Gardarin, "Join and semi-join algorithms for a multiprocessor database machine,"ACM Trans. Database Syst., vol. 9, no. 1, pp. 133-161, 1984.
[21] B. Wagar, "Hyperquicksort: A fast sorting algorithm for hypercubes," inProc. Hypercube Multiprocessors, 1987, pp. 292-299.

Index Terms:
data redistribution algorithms; hypercubes; database processing; parallel computer systems; data parallel algorithms; parallel algorithms; relational database join operation; cycling; global partitioning; tuple distribution method; time complexity; 64-node NCUBE; data partitions; computational complexity; database theory; hypercube networks; parallel algorithms; query processing; relational databases
C.K. Baru, S. Padmanabhan, "Join and Data Redistribution Algorithms for Hypercubes," IEEE Transactions on Knowledge and Data Engineering, vol. 5, no. 1, pp. 161-168, Feb. 1993, doi:10.1109/69.204100
Usage of this product signifies your acceptance of the Terms of Use.