Abstract
After the flow graph of an application has been clustered and the operation clusters have been assigned to ASUs, the next task is to determine the optimal composition of each ASU. A data-path structure that is capable of executing each of the assigned clusters as a different mode must be synthesised. In this chapter, a synthesis approach that works at the structural level will be investigated. The input to the synthesis problem is a set of clusters. These are graph structures whose nodes represent primitive functions or operations and for which there exists a mapping to one or more possible building block types (ABBs). The ASU that must be synthesised is a reconfigurable structure, which is composed of ABB instances and each configuration corresponds to the structure of one of the clusters.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1997 Springer Science+Business Media New York
About this chapter
Cite this chapter
Geurts, W., Catthoor, F., Vernalde, S., de Man, H. (1997). ASU Synthesis. In: Accelerator Data-Path Synthesis for High-Throughput Signal Processing Applications. Springer, Boston, MA. https://doi.org/10.1007/978-1-4419-8720-4_8
Download citation
DOI: https://doi.org/10.1007/978-1-4419-8720-4_8
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-4674-6
Online ISBN: 978-1-4419-8720-4
eBook Packages: Springer Book Archive