A stream-oriented parallel processing scheme is presented for relational database operations (relational operations). By combining the stream processing principle with demand-driven control, this scheme exploits the pipeline concurrency inherent in a query and makes it possible to execute relational operations with limited resources. A basic algorithm is presented for this stream-oriented scheme, and its features and effectiveness are discussed.
|Title of host publication||Proceedings of the International Conference on Parallel Processing|
|Editors||Kai Hwang, Steven M. Jacobs, Earl E. Swartzlander|
|Number of pages||8|
|Publication status||Published - 1986|
ASJC Scopus subject areas
- Hardware and Architecture