DocumentCode
1994283
Title
RTL Simulation of High Performance Dynamic Reconfiguration: A Video Processing Case Study
Author
Lingkan Gong ; Diessel, Oliver ; Paul, J. ; Stechele, Walter
Author_Institution
Sch. of Comput. Sci. & Eng., Univ. of New South Wales, Sydney, NSW, Australia
fYear
2013
fDate
20-24 May 2013
Firstpage
106
Lastpage
113
Abstract
Dynamically Reconfigurable Systems (DRS) allow hardware logic to be partially reconfigured while the rest of the design continues to operate. For example, the Auto Vision driver assistance system swaps video processing engines when the driving conditions change. However, the architectural flexibility of DRS also introduces challenges for verifying system functionality. Using Auto Vision as a case study, this paper studies the use of a recent RTL simulation library, ReSim, to perform functional verification of DRS designs. Compared with the conventional Virtual Multiplexing approach, ReSim more accurately simulates the Auto Vision system before, during and after reconfigurations. With trivial development and simulation overhead, ReSim assisted in detecting significantly more bugs than found using Virtual Multiplexing. To the best of our knowledge, this paper is the first significant effort towards functionally verifying a cutting-edge, complex, real-world DRS application.
Keywords
digital simulation; field programmable gate arrays; video signal processing; DRS designs; FPGA; RTL simulation; auto vision driver assistance system; dynamically reconfigurable systems; high performance dynamic reconfiguration; video processing case study; video processing engines; virtual multiplexing approach; Computer bugs; Engines; Field programmable gate arrays; Hardware; Image motion analysis; Multiplexing; Software; Dynamic Partial Reconfiguration; FPGA; Functional Verification; Simulation; Video Processing;
fLanguage
English
Publisher
ieee
Conference_Titel
Parallel and Distributed Processing Symposium Workshops & PhD Forum (IPDPSW), 2013 IEEE 27th International
Conference_Location
Cambridge, MA
Print_ISBN
978-0-7695-4979-8
Type
conf
DOI
10.1109/IPDPSW.2013.79
Filename
6650877
Link To Document