Low-Area/Power Parallel FIR Digital Filter Implementations

David A. Parker, Keshab K Parhi

Research output: Contribution to journalArticle

53 Citations (Scopus)

Abstract

This paper presents a novel approach for implementing area-efficient parallel (block) finite impulse response (FIR) filters that require less hardware than traditional block FIR filter implementations. Parallel processing is a powerful technique because it can be used to increase the throughput of a FIR filter or reduce the power consumption of a FIR filter. However, a traditional block filter implementation causes a linear increase in the hardware cost (area) by a factor of L, the block size. In many design situations, this large hardware penalty cannot be tolerated. Therefore, it is important to design parallel FIR filter structures that require less area than traditional block FIR filtering structures. In this paper, we propose a method to design parallel FIR filter structures that require a less-than-linear increase in the hardware cost. A novel adjacent coefficient sharing based sub-structure sharing technique is introduced and used to reduce the hardware cost of parallel FIR filters. A novel coefficient quantization technique, referred to as a scalable maximum absolute difference (MAD) quantization process, is introduced and used to produce quantized filters with good spectrum characteristics. By using a combination of fast FIR filtering algorithms, a novel coefficient quantization process and area reduction techniques, we show that parallel FIR filters can be implemented with up to a 45% reduction in hardware compared to traditional parallel FIR filters.

Original languageEnglish (US)
Pages (from-to)75-92
Number of pages18
JournalJournal of VLSI Signal Processing Systems for Signal, Image, and Video Technology
Volume17
Issue number1
StatePublished - Dec 1 1997

Fingerprint

Digital Filter
FIR filters
Impulse Response
Digital filters
Filter
Hardware
Quantization
Impulse response
Sharing
Costs
Coefficient
Filtering
Substructure
Parallel Processing
Electric power utilization
Power Consumption
Throughput
Penalty
Adjacent

Cite this

Low-Area/Power Parallel FIR Digital Filter Implementations. / Parker, David A.; Parhi, Keshab K.

In: Journal of VLSI Signal Processing Systems for Signal, Image, and Video Technology, Vol. 17, No. 1, 01.12.1997, p. 75-92.

Research output: Contribution to journalArticle

@article{4c303e5730274635b9b72eeb88b01d2c,
title = "Low-Area/Power Parallel FIR Digital Filter Implementations",
abstract = "This paper presents a novel approach for implementing area-efficient parallel (block) finite impulse response (FIR) filters that require less hardware than traditional block FIR filter implementations. Parallel processing is a powerful technique because it can be used to increase the throughput of a FIR filter or reduce the power consumption of a FIR filter. However, a traditional block filter implementation causes a linear increase in the hardware cost (area) by a factor of L, the block size. In many design situations, this large hardware penalty cannot be tolerated. Therefore, it is important to design parallel FIR filter structures that require less area than traditional block FIR filtering structures. In this paper, we propose a method to design parallel FIR filter structures that require a less-than-linear increase in the hardware cost. A novel adjacent coefficient sharing based sub-structure sharing technique is introduced and used to reduce the hardware cost of parallel FIR filters. A novel coefficient quantization technique, referred to as a scalable maximum absolute difference (MAD) quantization process, is introduced and used to produce quantized filters with good spectrum characteristics. By using a combination of fast FIR filtering algorithms, a novel coefficient quantization process and area reduction techniques, we show that parallel FIR filters can be implemented with up to a 45{\%} reduction in hardware compared to traditional parallel FIR filters.",
author = "Parker, {David A.} and Parhi, {Keshab K}",
year = "1997",
month = "12",
day = "1",
language = "English (US)",
volume = "17",
pages = "75--92",
journal = "Journal of Signal Processing Systems",
issn = "1939-8018",
publisher = "Springer New York",
number = "1",

}

TY - JOUR

T1 - Low-Area/Power Parallel FIR Digital Filter Implementations

AU - Parker, David A.

AU - Parhi, Keshab K

PY - 1997/12/1

Y1 - 1997/12/1

N2 - This paper presents a novel approach for implementing area-efficient parallel (block) finite impulse response (FIR) filters that require less hardware than traditional block FIR filter implementations. Parallel processing is a powerful technique because it can be used to increase the throughput of a FIR filter or reduce the power consumption of a FIR filter. However, a traditional block filter implementation causes a linear increase in the hardware cost (area) by a factor of L, the block size. In many design situations, this large hardware penalty cannot be tolerated. Therefore, it is important to design parallel FIR filter structures that require less area than traditional block FIR filtering structures. In this paper, we propose a method to design parallel FIR filter structures that require a less-than-linear increase in the hardware cost. A novel adjacent coefficient sharing based sub-structure sharing technique is introduced and used to reduce the hardware cost of parallel FIR filters. A novel coefficient quantization technique, referred to as a scalable maximum absolute difference (MAD) quantization process, is introduced and used to produce quantized filters with good spectrum characteristics. By using a combination of fast FIR filtering algorithms, a novel coefficient quantization process and area reduction techniques, we show that parallel FIR filters can be implemented with up to a 45% reduction in hardware compared to traditional parallel FIR filters.

AB - This paper presents a novel approach for implementing area-efficient parallel (block) finite impulse response (FIR) filters that require less hardware than traditional block FIR filter implementations. Parallel processing is a powerful technique because it can be used to increase the throughput of a FIR filter or reduce the power consumption of a FIR filter. However, a traditional block filter implementation causes a linear increase in the hardware cost (area) by a factor of L, the block size. In many design situations, this large hardware penalty cannot be tolerated. Therefore, it is important to design parallel FIR filter structures that require less area than traditional block FIR filtering structures. In this paper, we propose a method to design parallel FIR filter structures that require a less-than-linear increase in the hardware cost. A novel adjacent coefficient sharing based sub-structure sharing technique is introduced and used to reduce the hardware cost of parallel FIR filters. A novel coefficient quantization technique, referred to as a scalable maximum absolute difference (MAD) quantization process, is introduced and used to produce quantized filters with good spectrum characteristics. By using a combination of fast FIR filtering algorithms, a novel coefficient quantization process and area reduction techniques, we show that parallel FIR filters can be implemented with up to a 45% reduction in hardware compared to traditional parallel FIR filters.

UR - http://www.scopus.com/inward/record.url?scp=0031222835&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031222835&partnerID=8YFLogxK

M3 - Article

VL - 17

SP - 75

EP - 92

JO - Journal of Signal Processing Systems

JF - Journal of Signal Processing Systems

SN - 1939-8018

IS - 1

ER -