DIRECT - a multiprocessor organization for supporting relational data base management systems

The design of DIRECT, a multiprocessor organization for supporting relational data base management systems is presented. DIRECT has a MIMD (multiple instruction stream, multiple data stream) architecture. It can simultaneously support both intra-query and inter-query concurrency. The number of processors assigned to a query is dynamically determined by the priority of the query and the size of the relations it references. The size of a relation is not limited to that of the associative memory as in some previous data base machines. Concurrent updates are controlled through address translation tables which are maintained by a controlling processor. DIRECT is being implemented using LSI-11/03 microprocessors and CCD memories which are searched in an associative manner. A novel cross-point switch is used to connect the LSI-11 processors to the CCD memories. While cross-point switches have proven too expensive for use in general purpose parallel processors, their application in DIRECT demonstrates that these switches can be successfully used in specialized applications.

[1]  Gordon Bell,et al.  C.mmp: a multi-mini-processor , 1972, AFIPS '72 (Fall, part II).

[2]  Michael Stonebraker,et al.  INGRES: a relational data base system , 1975, AFIPS '75.

[3]  G. Jack Lipovski,et al.  The architecture of a context addressed segment-sequential storage , 1972, AFIPS '72 (Fall, part II).

[4]  Kenneth C. Smith,et al.  A virtual memory system for a relational associative processor , 1976, SIGF.

[5]  Evan L. Ivie,et al.  A back-end computer for data base management , 1974, CACM.

[6]  Chyuan Shiun Lin,et al.  The design of a rotating associative memory for relational database applications , 1976, TODS.

[7]  Kenneth C. Smith,et al.  RAP: an associative processor for data base management , 1975, AFIPS '75.

[8]  Stanley Y. W. Su,et al.  A high level data sublanguage for a context-addressed segment-sequential memory , 1974, SIGFIDET '74.

[9]  Daniel L. Slotnick.  Logic per Track Devices , 1970, Adv. Comput..

[10]  N. Minsky.  Rotating Storage Devices As Partially Associative Memories , 1972, SIGFIDET Workshop.

[11]  Behrooz Parhami.  A highly parallel computing system for information retrieval , 1972, AFIPS '72 (Fall, part II).

[12]  Eugene Wong,et al.  Decomposition—a strategy for query processing , 1976, TODS.

[13]  Stanley Y. W. Su,et al.  The architecture of CASSM: A cellular system for non-numeric processing , 1973, ISCA 1973.

[14]  G. Jack Lipovski,et al.  Retrieval operations and data representations in a context-addressed disc system , 1975 .

[15]  Michael Stonebraker,et al.  The design and implementation of INGRES , 1976, TODS.

[16]  James L. Parker,et al.  A Logic-Per-Track Retrieval System , 1971, IFIP Congress.

[17]  Diane C. P. Smith,et al.  The design of a rotating associative array memory for a relational data base management application , 1975, SIGF.