By Topic

Performance evaluation of parallel architectures in real-time implementation of adaptive filtering algorithms

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $33
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
M. O. Tokhi ; Sheffield Univ., UK ; M. A. Hossain

Explores the real-time performance of a number of parallel and sequential hardware architectures for the LMS and RLS adaptive filters. Throughout the investigations, it is seen that the C40+C40 based architecture with its powerful DSP resources performs as the fastest computing domain for both algorithms. The disparity among the relative processing times indicates a mismatch between the hardware requirements of the algorithms and the hardware resources of the architectures. Therefore, to fully exploit the architectures a close match needs to be forged between the algorithm and the underlying hardware, and issues such as algorithmic regularity and granularity need to be considered during an implementation process. A comparative performance of architectures demonstrated the need for utilisation of fast DSP and PP techniques in signal processing applications which involve complex and computationally intensive algorithms.<>

Published in:

1990 IEE Colloquium on Digital and Analogue Filters and Filtering Systems (Digest No. 1990/091)

Date of Conference:

25-25 May 1990