Abstract
This paper presents a memory-centric communication architecture for a reconfigurable array of processing elements, which reduces the communication overhead by establishing a direct communication channel through a memory between the array and other masters in the system. Not to increase the area cost too much, we do not use a multi-port memory, but divide the memory into multiple memory units, each having a single port. The masters and the memory units have one-to-one mapping through a simple crossbar switch, which switches whenever data transfer is needed. Experimental results show that the proposed architecture achieves 76% performance improvement over the conventional architecture.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Hartenstein, R.: A decade of reconfigurable computing: a visionary retrospective. In: Proc. DATE (2001)
Singh, H., et al.: MorphoSys: an integrated reconfigurable system for data-parallel and computation-intensive application. IEEE Trans. on Computers 49(5) (2000)
Kim, et al.: Design and evaluation of coarse-grained reconfigurable architecture. In: Proc. ISOCC (2004)
Carbon SoC Designer, http://www.carbondesignsystems.com/Products/SoCDesigner.aspx
Lee, H., Choi, K.: Multi-codec variable length decoder design with configurable processor. In: Proc. ISOCC (2008)
Jo, M., et al.: Implementation of floating-point operations for 3D graphics on a coarse-grained reconfigurable architecture. In: Proc. IEEE SOCC (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chang, K., Choi, K. (2010). Memory-Centric Communication Architecture for Reconfigurable Computing. In: Sirisuk, P., Morgan, F., El-Ghazawi, T., Amano, H. (eds) Reconfigurable Computing: Architectures, Tools and Applications. ARC 2010. Lecture Notes in Computer Science, vol 5992. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-12133-3_40
Download citation
DOI: https://doi.org/10.1007/978-3-642-12133-3_40
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-12132-6
Online ISBN: 978-3-642-12133-3
eBook Packages: Computer ScienceComputer Science (R0)