Reconfiguration of IIR filters in response to computer resource availability

Authors:
B. H. Ferri;A. A. Ferri
Affiliations:
Georgia Institute of Technology, Atlanta, GA;Georgia Institute of Technology, Atlanta, GA
Venue:
ACM Transactions on Embedded Computing Systems (TECS)
Year:
2009

Citing 8
Cited 0

Approximate Signal Processing

Journal of VLSI Signal Processing Systems - Special issue on the rapid prototyping of application specific signal processors (RASSP) program
Advanced Signal Processing Handbook: Theory and Implementation for Radar, Sonar, and Medical Imaging Real-Time Systems

Advanced Signal Processing Handbook: Theory and Implementation for Radar, Sonar, and Medical Imaging Real-Time Systems
Imprecise and Approximate Computation

Imprecise and Approximate Computation
Resource Management in Real-Time Systems and Networks

Resource Management in Real-Time Systems and Networks
Computer architecture: a quantitative approach

Computer architecture: a quantitative approach
2001 IEEE International Conference on Acoustics, Speech, and Signal Processing

ICASSP '01 Proceedings of the Acoustics, Speech, and Signal Processing, 200. on IEEE International Conference - Volume 02
Suppression of transients in variable recursive digital filterswith a novel and efficient cancellation method

IEEE Transactions on Signal Processing
The L2 (l2) bumpless transfer problem for linear plants: Its definition and solution

Automatica (Journal of IFAC)

Quantified Score

Hi-index	0.00

Visualization

Abstract

This article explores methods to reconfigure infinite impulse response (IIR) filters in processes that utilize computer resource management. A high-performance mode uses a full-length IIR filter, while low resources or a desire to conserve power triggers a low-performance mode where a smaller length filter is used. Two alternatives for algorithms are explored: switching between filter banks of varying lengths, and anytime filters where the later stages can be skipped if computational resources are scarce. Two main challenges are addressed in this article. The first is how to configure an IIR filter as an anytime algorithm, and the second is how to initialize the states of the filters in order to mitigate transients induced by reconfiguration. The performance and feasibility of several common transient management schemes are investigated for use in this application. It is found that an anytime IIR filter outperforms the filter banks in almost every case studied due to its inherently smaller transients and the fact that the reconfiguration happens at the speed of resource management and not at a lower speed typically associated with reconfiguration due to physical system properties.