Asynchronous integration of coarse-grained reconfigurable XPP-arrays into pipelined risc processor datapath

0Citations
Citations of this article
5Readers
Mendeley users who have this article in their library.

This article is free to access.

Abstract

Nowadays, the datapaths of modern microprocessors reach their limits by using static instruction sets. A way out of these limitations is a dynamic reconfigurable processor datapath extension achieved by integrating traditional static datapaths with the coarse-grain dynamic reconfigurable XPP-architecture (eXtreme Processing Platform). Therefore, a loosely asynchronous coupling mechanism of the corresponding datapath units has been developed and integrated onto a CMOS 0.13 μm standard cell technology from UMC. Here the SPARC compatible LEON processor is used, whereas its static pipelined instruction datapath has been extended to be configured and personalized for specific applications. This allows a various and efficient use, e.g. in streaming application domains like MPEG-4, digital filters, mobile communication modulation, etc. The chosen coupling technique allows asynchronous concurrency of the additionally configured compound instructions, which are integrated into the programming and compilation environment of the LEON processor. © 2006 International Federation for Information Processing.

Cite

CITATION STYLE

APA

Becker, J., Thomas, A., & Scheer, M. (2006). Asynchronous integration of coarse-grained reconfigurable XPP-arrays into pipelined risc processor datapath. IFIP International Federation for Information Processing, 200, 263–279. https://doi.org/10.1007/0-387-33403-3_17

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free