Parallel and Distributed Databases

Publications on Parallel and Distributed Databases

A Cost Model for the Estimation of Query Execution Time in a Parallel Environment Supporting Pipeline

M. Spiliopoulou, M. Hatzopoulos and C. Vassilakis
in Journal Computers and Artificial Intelligence, Vol. 14, 1996, No. 1, pp. 341-368

Abstract:
We propose a model for the estimation of query execution time in an environment supporting bushy and pipelined parallelism. We consider a parallel architecture of processors having private main memories, accessing a shared secondary storage and communicating to each other via a network. For this environment, we compute the cost of query operators when processed in isolation and when in pipeline mode. We use those formulae to incrementally compute the cost of a query execution plan from its components. Our cost model can be incorporated to any optimizer for parallel query processing that considers parallel and pipelined execution of the query operators.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.
AttachmentSize
PDF icon cost-model-95.pdf259.36 KB
Year: 

Parallel Optimisation of Join Queries Using a Technique of Exhaustive Nature

M. Spiliopoulou, M. Hatzopoulos and C. Vassilakis
in Computers and Artificial Intelligence, Vol. 12, 1993, No. 2.

Abstract
In this study we present a technique for the parallel optimisation of join queries, that uses the offered coarse-grain parallelism of the underlying architecture in order to reduce the CPU-bound optimisation overhead. The optimisation technique performs an almost exhaustive search of the solution space for small join queries and gradually, as the number of joins increases, it diverges towards iterative improvement. This technique has been developed on a low-parallelism transputer-based architecture, where its behaviour is studied for the optimisation of queries with many tenths of joins.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.
AttachmentSize
PDF icon cai-93.pdf248.77 KB
Year: 

Using Parallelism and Pipeline for the Optimisation of Join Queries

M. Spiliopoulou, M. Hatzopoulos and C. Vassilakis
Proceedings of the PARLE Conference, Paris, June 1992

Abstract
In this study we present a technique for the parallel optimisation of join queries, that uses the offered coarse-grain parallelism of the underlying architecture in order to reduce the CPU-bound optimisation overhead. The optimisation technique performs an almost exhaustive search of the solution space for small join queries and gradually, as the number of joins increases, it diverges towards iterative improvement. This technique has been developed on a low-parallelism transputer-based architecture, where its behaviour is studied for the optimisation of queries with many tenths of joins.

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.
AttachmentSize
PDF icon parle-paper.pdf495.03 KB
Year: