ACM Transactions on Database Systems (TODS)
Concepts and capabilities of a database computer\
ACM Transactions on Database Systems (TODS)
A relational model of data for large shared data banks
Communications of the ACM
The architecture of CASSM: A cellular system for non-numeric processing
ISCA '73 Proceedings of the 1st annual symposium on Computer architecture
A specialized computer architecture for text retrieval
CAW '78 Proceedings of the fourth workshop on Computer architecture for non-numeric processing
A machine for information retrieval
CAW '78 Proceedings of the fourth workshop on Computer architecture for non-numeric processing
A Special-Function Unit for Sorting and Sort-Based Database Operations
IEEE Transactions on Computers
Performance Analysis of a Database Filter Search Hardware
IEEE Transactions on Computers
Join processing in relational databases
ACM Computing Surveys (CSUR)
Join and Semijoin Algorithms for a Multiprocessor Database Machine
ACM Transactions on Database Systems (TODS)
Relational queries in a domain based DBMS
SIGMOD '83 Proceedings of the 1983 ACM SIGMOD international conference on Management of data
A domain based internal schema for relational database machines
SIGMOD '82 Proceedings of the 1982 ACM SIGMOD international conference on Management of data
The schuss filter: A processor for non-numerical data processing.
ISCA '84 Proceedings of the 11th annual international symposium on Computer architecture
A performance evaluation of data base machine architectures (invited paper)
VLDB '81 Proceedings of the seventh international conference on Very Large Data Bases - Volume 7
Exploiting parallelism for the performance enhancement of non-numeric applications
AFIPS '82 Proceedings of the June 7-10, 1982, national computer conference
Hi-index | 0.01 |
Most data base machines use some type of "filter" to perform unary operations on files. This filter processes information "on the fly" during its transfer from mass storage (Disk) to main storage (main memory or buffer). This paper is devoted to the design study of such a filter for relational-type data bases. It is therefore assumed that data are structured as a set of n-ary relations.Using a top-down approach we classify the requirements under two catagories:1) Functional specification of the filter: the filter should perform the unary relational operations i.e. projection and restriction; it should also permit insertion deletion and updates of tuples.2) Performance requirements: in a filtering system access time is a linear function of the space used to the store relations, it becomes therefore of the utmost importance to minimize this space.In order to meet the second requirement, we suggest to structure the n-ary relations into hierarchical free format files. Clearly, such a data structure minimizes space: the remaining problems being the ability to read and update such files. It is then shown that an automaton-like device is sufficient to perform projections and restrictions of relations and insertions, deletions and updates of tuples. That device is described and an algorithm that automatically generates the microprogram realizing that device from the description of the relation and that of the operations to be performed is given.