Enhancing a Hearing Aid Processor with ISA Extensions Supporting Flexible Fixed-Point Formats

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

View graph of relations

Details

Original languageEnglish
Title of host publicationProceedings - 2024 IEEE 35th International Conference on Application-Specific Systems, Architectures and Processors, ASAP 2024
Pages176-183
Number of pages8
ISBN (electronic)979-8-3503-4963-4
Publication statusPublished - 2024

Publication series

NameEEE International Conference on Application-Specific Systems, Architectures, and Processors
ISSN (Print)2160-0511
ISSN (electronic)2160-052X

Abstract

As the number of individuals experiencing hearing problems rises, research in this area is increasing. In particular, algorithms for enhancing sound quality are becoming more advanced. However, the energy consumption of hearing aids is restricted to a few milliwatts. New hearing aid processors and hardware must be developed to tackle this issue. Therefore, this paper presents and evaluates custom hardware units for hearing aids suitable for flexible fixed-point formats. The units are added to the instruction set architecture (ISA) of a Tensilica Fusion G6. This is one of two high-level programmable application-specific instruction-set processors (ASIP) integrated into the Smart Hearing Aid Processor (SmartHeaP), a hearing aid system-on-chip (SoC) fabricated in 22nm fully depleted silicon on insulator (FD-SOI) technology. As many audio algorithms operate in the frequency domain, complex-domain units like a complex multiply-accumulate (CMAC) unit are introduced first. Additionally, coordinate rotation digital computer (CORDIC) operations have been added to speed up nonlinear functions such as logarithms, another function frequently used in hearing aid applications. The implemented extensions are integrated into a MATLAB fixed-point framework to simplify access to the ISA extensions for algorithm developers. It automatically generates fixed-point C code with direct access to the added instructions, reducing development time and complexity. Integrating the seven proposed instructions with corresponding register files increases the core area by 20% or 0.065 mm 2in a 22nm front-end synthesis. On the other hand, these extensions reduce the cycle count for two evaluated hearing aid algorithms, a beamformer and a loudness compensator, by 93% and 38%. A reduction of up to 84% is achieved for standalone mathematical functions, like logarithmic calculations. These performance improvements directly translate into power savings by allowing a reduced clock frequency.

Keywords

    CMAC, CORDIC, ISA extension, MATLAB, SmartHeaP, Tensilica, fixed-point arithmetic

ASJC Scopus subject areas

Sustainable Development Goals

Cite this

Enhancing a Hearing Aid Processor with ISA Extensions Supporting Flexible Fixed-Point Formats. / Karrenbauer, Jens; Schönewald, Sven; Klein, Simon et al.
Proceedings - 2024 IEEE 35th International Conference on Application-Specific Systems, Architectures and Processors, ASAP 2024. 2024. p. 176-183 (EEE International Conference on Application-Specific Systems, Architectures, and Processors).

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Karrenbauer, J, Schönewald, S, Klein, S & Blume, H 2024, Enhancing a Hearing Aid Processor with ISA Extensions Supporting Flexible Fixed-Point Formats. in Proceedings - 2024 IEEE 35th International Conference on Application-Specific Systems, Architectures and Processors, ASAP 2024. EEE International Conference on Application-Specific Systems, Architectures, and Processors, pp. 176-183. https://doi.org/10.1109/asap61560.2024.00044
Karrenbauer, J., Schönewald, S., Klein, S., & Blume, H. (2024). Enhancing a Hearing Aid Processor with ISA Extensions Supporting Flexible Fixed-Point Formats. In Proceedings - 2024 IEEE 35th International Conference on Application-Specific Systems, Architectures and Processors, ASAP 2024 (pp. 176-183). (EEE International Conference on Application-Specific Systems, Architectures, and Processors). https://doi.org/10.1109/asap61560.2024.00044
Karrenbauer J, Schönewald S, Klein S, Blume H. Enhancing a Hearing Aid Processor with ISA Extensions Supporting Flexible Fixed-Point Formats. In Proceedings - 2024 IEEE 35th International Conference on Application-Specific Systems, Architectures and Processors, ASAP 2024. 2024. p. 176-183. (EEE International Conference on Application-Specific Systems, Architectures, and Processors). doi: 10.1109/asap61560.2024.00044
Karrenbauer, Jens ; Schönewald, Sven ; Klein, Simon et al. / Enhancing a Hearing Aid Processor with ISA Extensions Supporting Flexible Fixed-Point Formats. Proceedings - 2024 IEEE 35th International Conference on Application-Specific Systems, Architectures and Processors, ASAP 2024. 2024. pp. 176-183 (EEE International Conference on Application-Specific Systems, Architectures, and Processors).
Download
@inproceedings{027344ab9e4240a9a556c22b420152ca,
title = "Enhancing a Hearing Aid Processor with ISA Extensions Supporting Flexible Fixed-Point Formats",
abstract = "As the number of individuals experiencing hearing problems rises, research in this area is increasing. In particular, algorithms for enhancing sound quality are becoming more advanced. However, the energy consumption of hearing aids is restricted to a few milliwatts. New hearing aid processors and hardware must be developed to tackle this issue. Therefore, this paper presents and evaluates custom hardware units for hearing aids suitable for flexible fixed-point formats. The units are added to the instruction set architecture (ISA) of a Tensilica Fusion G6. This is one of two high-level programmable application-specific instruction-set processors (ASIP) integrated into the Smart Hearing Aid Processor (SmartHeaP), a hearing aid system-on-chip (SoC) fabricated in 22nm fully depleted silicon on insulator (FD-SOI) technology. As many audio algorithms operate in the frequency domain, complex-domain units like a complex multiply-accumulate (CMAC) unit are introduced first. Additionally, coordinate rotation digital computer (CORDIC) operations have been added to speed up nonlinear functions such as logarithms, another function frequently used in hearing aid applications. The implemented extensions are integrated into a MATLAB fixed-point framework to simplify access to the ISA extensions for algorithm developers. It automatically generates fixed-point C code with direct access to the added instructions, reducing development time and complexity. Integrating the seven proposed instructions with corresponding register files increases the core area by 20% or 0.065 mm 2in a 22nm front-end synthesis. On the other hand, these extensions reduce the cycle count for two evaluated hearing aid algorithms, a beamformer and a loudness compensator, by 93% and 38%. A reduction of up to 84% is achieved for standalone mathematical functions, like logarithmic calculations. These performance improvements directly translate into power savings by allowing a reduced clock frequency.",
keywords = "CMAC, CORDIC, ISA extension, MATLAB, SmartHeaP, Tensilica, fixed-point arithmetic",
author = "Jens Karrenbauer and Sven Sch{\"o}newald and Simon Klein and Holger Blume",
note = "Publisher Copyright: {\textcopyright} 2024 IEEE.",
year = "2024",
doi = "10.1109/asap61560.2024.00044",
language = "English",
isbn = "979-8-3503-4964-1",
series = "EEE International Conference on Application-Specific Systems, Architectures, and Processors",
pages = "176--183",
booktitle = "Proceedings - 2024 IEEE 35th International Conference on Application-Specific Systems, Architectures and Processors, ASAP 2024",

}

Download

TY - GEN

T1 - Enhancing a Hearing Aid Processor with ISA Extensions Supporting Flexible Fixed-Point Formats

AU - Karrenbauer, Jens

AU - Schönewald, Sven

AU - Klein, Simon

AU - Blume, Holger

N1 - Publisher Copyright: © 2024 IEEE.

PY - 2024

Y1 - 2024

N2 - As the number of individuals experiencing hearing problems rises, research in this area is increasing. In particular, algorithms for enhancing sound quality are becoming more advanced. However, the energy consumption of hearing aids is restricted to a few milliwatts. New hearing aid processors and hardware must be developed to tackle this issue. Therefore, this paper presents and evaluates custom hardware units for hearing aids suitable for flexible fixed-point formats. The units are added to the instruction set architecture (ISA) of a Tensilica Fusion G6. This is one of two high-level programmable application-specific instruction-set processors (ASIP) integrated into the Smart Hearing Aid Processor (SmartHeaP), a hearing aid system-on-chip (SoC) fabricated in 22nm fully depleted silicon on insulator (FD-SOI) technology. As many audio algorithms operate in the frequency domain, complex-domain units like a complex multiply-accumulate (CMAC) unit are introduced first. Additionally, coordinate rotation digital computer (CORDIC) operations have been added to speed up nonlinear functions such as logarithms, another function frequently used in hearing aid applications. The implemented extensions are integrated into a MATLAB fixed-point framework to simplify access to the ISA extensions for algorithm developers. It automatically generates fixed-point C code with direct access to the added instructions, reducing development time and complexity. Integrating the seven proposed instructions with corresponding register files increases the core area by 20% or 0.065 mm 2in a 22nm front-end synthesis. On the other hand, these extensions reduce the cycle count for two evaluated hearing aid algorithms, a beamformer and a loudness compensator, by 93% and 38%. A reduction of up to 84% is achieved for standalone mathematical functions, like logarithmic calculations. These performance improvements directly translate into power savings by allowing a reduced clock frequency.

AB - As the number of individuals experiencing hearing problems rises, research in this area is increasing. In particular, algorithms for enhancing sound quality are becoming more advanced. However, the energy consumption of hearing aids is restricted to a few milliwatts. New hearing aid processors and hardware must be developed to tackle this issue. Therefore, this paper presents and evaluates custom hardware units for hearing aids suitable for flexible fixed-point formats. The units are added to the instruction set architecture (ISA) of a Tensilica Fusion G6. This is one of two high-level programmable application-specific instruction-set processors (ASIP) integrated into the Smart Hearing Aid Processor (SmartHeaP), a hearing aid system-on-chip (SoC) fabricated in 22nm fully depleted silicon on insulator (FD-SOI) technology. As many audio algorithms operate in the frequency domain, complex-domain units like a complex multiply-accumulate (CMAC) unit are introduced first. Additionally, coordinate rotation digital computer (CORDIC) operations have been added to speed up nonlinear functions such as logarithms, another function frequently used in hearing aid applications. The implemented extensions are integrated into a MATLAB fixed-point framework to simplify access to the ISA extensions for algorithm developers. It automatically generates fixed-point C code with direct access to the added instructions, reducing development time and complexity. Integrating the seven proposed instructions with corresponding register files increases the core area by 20% or 0.065 mm 2in a 22nm front-end synthesis. On the other hand, these extensions reduce the cycle count for two evaluated hearing aid algorithms, a beamformer and a loudness compensator, by 93% and 38%. A reduction of up to 84% is achieved for standalone mathematical functions, like logarithmic calculations. These performance improvements directly translate into power savings by allowing a reduced clock frequency.

KW - CMAC

KW - CORDIC

KW - ISA extension

KW - MATLAB

KW - SmartHeaP

KW - Tensilica

KW - fixed-point arithmetic

UR - http://www.scopus.com/inward/record.url?scp=85203108425&partnerID=8YFLogxK

U2 - 10.1109/asap61560.2024.00044

DO - 10.1109/asap61560.2024.00044

M3 - Conference contribution

SN - 979-8-3503-4964-1

T3 - EEE International Conference on Application-Specific Systems, Architectures, and Processors

SP - 176

EP - 183

BT - Proceedings - 2024 IEEE 35th International Conference on Application-Specific Systems, Architectures and Processors, ASAP 2024

ER -

By the same author(s)