Abstract
The main driving forces for parallel processing are the need and desire for higher performance, better cost/performance ratio, and improved scalability. This Chapter reviews basic concepts about parallel processing, in the context of databases. We first introduce the difference between temporal and spatial parallelism, the concepts of granularity, level and degree of parallelism, and the differences between shared memory and distributed memory architectures. We then discuss some metrics to evaluate the performance of parallel systems, such as speed up, efficiency and scale up. Next we discuss two important issues that must be well managed for maximizing these metrics, namely the issues of communication overhead and load balancing. Finally, we discuss three alternative ways to exploit parallelism, namely automatic parallelization, modifying an existing sequential algorithm or designing a new parallel algorithm from the scratch.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer Science+Business Media New York
About this chapter
Cite this chapter
Freitas, A.A., Lavington, S.H. (2000). Basic Concepts on Parallel Processing. In: Mining Very Large Databases with Parallel Processing. The Kluwer International Series on Advances in Database Systems, vol 9. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-5521-6_7
Download citation
DOI: https://doi.org/10.1007/978-1-4615-5521-6_7
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-7523-4
Online ISBN: 978-1-4615-5521-6
eBook Packages: Springer Book Archive