ABSTRACT
Specialized, single function processors can be built to be faster and cheaper than general purpose processors. Most database machines use such special purpose processors to manipulate data, with a general purpose managing processor to control the special purpose processors and perform utility functions. In this paper, the organization and use of these data manipulation processors is explored. Database machines are classified into single data manipulation processor systems, multiple disk-associated data manipulation processor systems, and multiple cache-associated processor systems. Examples of actual database machines are given for each category.Application types are classified into business, bibliographic search, and statistical analysis systems. A metric is developed to compare the performance of the categories of database machines with respect to the application types. The metric is the effective instruction rate, which is comparable to the instruction rate (millions of instructions per second) for conventional computers. It is shown that the effective instruction rate is highly sensitive to the proportion of work performed in the database machine's data manipulation processors. Therefore, determining the work that must be performed in the machine's managing processor is found to be important to determining the performance of the machine.Database machine performance for each category of database machines is compared for each type of application. It is shown that single processor systems are best for business applications; that disk-based multiple processor systems are best for bibliographic search applications; and that hybrid systems are best for statistical analysis applications. Therefore, the design of the organization of data manipulation processors is shown to be application-dependent.
- {BABB79} Babb, E., "Implementing a Relational database by Means of Specialized Hardware," ACM Transactions on Database Systems, Vol. 4, No. 1, March 1979, pp.1--29. Google ScholarDigital Library
- {BAN78A} Banerjee, J., and D.K. Hsiao, "Performance Study of a Database Machine in Supporting Relational Databases," Proc. Fourth International Conference on VLDB, 1978.Google Scholar
- {BAN78B} Banerjee, J., and D.K. Hsiao, "The Use of a 'Non-Relational' Database Machine in Supporting Relational Databases," Proc. Fourth Workshop on Computer Architecture for Non-numeric Processing, Syracuse, Aug. 1978. Google ScholarDigital Library
- {BANC80} Bancilhon, F., "VERSO: A Back-end Relational Machine," Proc. Sixth VLDB, 1980, p.394.Google Scholar
- {BAUM76}, Baum, Richard I., D. K. Hsaio and K. Kannan, "The Architecture of a Database Computer --- Part I: Concepts and Capabilities," National Technical Information Service Number AD-A034 154Google Scholar
- {BORA79} Boral, H., and D.J. DeWitt, "Processor Allocation Strategies for Multiprocessor Database Machines," Computer Sciences Technical Report No. 368, University of Wisconsin, Oct. 1979.Google Scholar
- {BORA80} Boral, H., D.J. DeWitt, D. Friedland and W.K. Wilkenson, "Parallel Algorithms for the Execution of Relational Database Operations" Computer Sciences Technical Report no. 402, University of Wisconsin-Madison, October, 1980.Google Scholar
- {BRIT80} Britton-Lee, Inc. "IDM 500 Intelligent Database Machine Product Description,", Britton-Lee Inc., 90 Albright Way, Los Gatos 95030.Google Scholar
- {COUL72} Coulouris, G.F., Evans, J.M., and R.W.Mitchell, "Towards Content Addressing in Databases," Computer Journal, Vol. 15, No. 2, 1972, pp. 95--98.Google ScholarCross Ref
- {DEWI78} Dewitt, D.J., "DIRECT --- A Multiprocessor Organization for Supporting Relational Data Base Management Systems," Proc. Fifth Annual Symposium on Computer Architecture, 1978. Google ScholarDigital Library
- {DEWI79} Dewitt, D.J., "Query Execution in DIRECT", Proceedings of the ACM-SIGMOD 1979 International Conference on Management of Data, May 1979, pp 13--22. Google ScholarDigital Library
- {EPS80A} Epstein, Robert and Paula Hawthorn, "Aid in the '80s," Datamation, Feb. 1980, pp. 156--158.Google Scholar
- {EPS80B} Epstein, Robert and Paula Hawthorn, "Design Decisions for the Intelligent Database Machine", Proceedings 1980 NCC, AFIPS Vol. 49, pp.237--241.Google Scholar
- {HAWT79} Hawthorn, Paula and M. Stone-braker, "Performance Analysis of a Relational Database Management System," Proceedings of the ACM-SIGMOD 1979 International Conference on Management of Data, May 1979, pp 1--12. Google ScholarDigital Library
- {HAWT80} Hawthorn, Paula, and D. J. Dewitt, "Performance Analysis of Alternative Database Machine Architectures," Computer Sciences Technical Report no. 383, University of Wisconsin-Madison, March 1980.Google Scholar
- {HSIA79} Hsiao, D.K. and J. Memon, "The Post Processing Functions of a Database Computer," Computer and Informtion Science Technical Report OSU-CISRC-TR-76-2, Ohio State University, 1979.Google Scholar
- {HSI76A} Hsiao, D.K., and K. Kannan "The Architecture of a Database Computer --- Part II: The Design of Structure Memory and its Related Processors," National Technical Information Service Number AD/A035 178Google Scholar
- {HSI76B} Hsiao, D.K., and K. Kannan, "The Architecture of a Database Computer --- Part III: The Design of Mass Memory and its Related Components," National Technical Information Service Number AD-A036 217Google Scholar
- {KANN78} Kannan, K., "The Design of a Mass Memory for a Database Computer," Proc. Fifth Annual IEEE Symposium on Computer Architecture April 1978. Google ScholarDigital Library
- {LIPO78} Lipovski, G. J., "Architectural Features of CASSM: a Context Addressed Segment Sequential Memory", Proc. Fifth Annual IEEE Symposium on Computer Architecture, April 1978. Google ScholarDigital Library
- {OZKA75} Ozkarahan, E.A., S.A. Schuster, and K.C. Sevcik, "RAP --- Associative Processor for Database Management," AFIPS Conference Proceedings, Vol. 44, 1975, pp. 379--388Google Scholar
- {OZKA77} Ozkarahan, E.A., S.A. Schuster, and K.C. Sevcik, "Performance Evaluation of a Relational Associative Processor," ACM Transactions on Database Systems, Vol. 2, No. 2, June 1977. Google ScholarDigital Library
- {ROSE77} Rosenthal, R.S., "The Data Management Machine, A Classification," ACM Sigir-Sigarch-Sigmod Third Workshop on Computer Architecture, Syracuse, New York, pp. 35--37. Google ScholarDigital Library
- {SADO78} Sadowski, Paul W. and S.A. Schuster, "Exploiting Parallelism in a Relational Associative Processor,", Proceedings Fourth Workshop on Computer Architecture for Non-Numeric Processing, August, 1978. Google ScholarDigital Library
- {SCHU78} Schuster, S.A., et. al., "RAP.2 --- An Associative Processor for Data Bases", Proceedings, Fifth Annual IEEE Symposium for Computer Architecture, April, 1978. Google ScholarDigital Library
- {SHAW80} Shaw, David E., "A Relational Database Machine Architecture", Proceedings Fifth Workshop on Computer Architecture for Non-Numeric Processing, March, 1980. Google ScholarDigital Library
- {SMIT79} Smith, Diane C.P., and J.M. Smith, "Relational Data Base Machines," IEEE Computer, March 1979, pp. 28--38.Google ScholarDigital Library
- {SU75} Su, S.Y.W. and G.J. Lipovski, "CASSM: A Cellular System for Very Large Data Bases", Proceedings of the VLDB, 1975, pp. 456--472.Google ScholarCross Ref
- {SU79} Su, S.Y.W., "Cellular-Logic Devices: Concepts and Applications", IEEE Computer, March 1979, pp. 11--28.Google Scholar
Recommendations
Branch Target Buffer Design and Optimization
A branch target buffer (BTB) can reduce the performance penalty of branches in pipelined processors by predicting the path of the branch and caching information used by the branch. Two major issues in the design of BTBs that achieves maximum performance ...
Comments