Abstract
We have seen that data dependencies hamper automatic parallelization of imperative programs. We have also seen that a general method to reduce the number of dependencies is to change writes so that they access distinct memory locations, that is, to expand data structures. However, expanding data structures has a cost. The increase in memory is an obvious cost. However, other costs discussed below may also be incurred. Therefore, a general problem arises: Given a cost criterion, what expansion provides maximum parallelism at the lowest cost?
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag New York, Inc.
About this chapter
Cite this chapter
(2003). Maximal Static Expansion. In: Collard, JF. (eds) Reasoning About Program Transformations. Springer, New York, NY. https://doi.org/10.1007/978-0-387-22461-9_9
Download citation
DOI: https://doi.org/10.1007/978-0-387-22461-9_9
Publisher Name: Springer, New York, NY
Print ISBN: 978-0-387-95391-5
Online ISBN: 978-0-387-22461-9
eBook Packages: Springer Book Archive