KAVUAKA: A Low Power Application Specific Hearing Aid Processor

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

Authors

Research Organisations

View graph of relations

Details

Original languageEnglish
Title of host publication2019 IFIP/IEEE 27th International Conference on Very Large Scale Integration (VLSI-SoC)
Subtitle of host publicationProceedings
EditorsCarolina Metzler, Giovanni De Micheli, Pierre-Emmanuel Gaillardon, Carlos Silva-Cardenas, Ricardo Reis
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages99-104
Number of pages6
ISBN (electronic)978-1-7281-3915-9
ISBN (print)978-1-7281-3916-6
Publication statusPublished - Oct 2019
Event27th IFIP/IEEE International Conference on Very Large Scale Integration, VLSI-SoC 2019 - Cuzco, Peru
Duration: 6 Oct 20199 Oct 2019

Publication series

NameInternational Conference on VLSI and System-on-Chip
ISSN (Print)2324-8432
ISSN (electronic)2324-8440

Abstract

The integration of application specific instruction set processors (ASIPs) in hearing aids requires various architectural customizations and software-side optimizations in order to meet the stringent power consumption constraints and processing performance demands. This paper presents the KAVUAKA application specific hearing aid processor and its ASIC integration as a system on chip (SoC). The final system contains four KAVUAKA processor cores and ten co-processors. Each of these processors and co-processors were individually customized and differ in their data path width. The processors are organized in two clusters, which share memories, an audio interface, co-processors and a serial interface. With this system, different hearing aid systems are evaluated in terms of performance, power and area by activating different processor and co-processor combinations. A 40 nm low power technology was used to build this research hearing aid system. The die size is 3.6 mm 2 with less than 1 mm 2 per core. The measured average power consumption is less than 1 mW per core.

Keywords

    asic, asip, hearing aid, low-power, processor, system on chip

ASJC Scopus subject areas

Sustainable Development Goals

Cite this

KAVUAKA: A Low Power Application Specific Hearing Aid Processor. / Gerlach, Lukas; Paya-Vaya, Guillermo; Blume, Holger.
2019 IFIP/IEEE 27th International Conference on Very Large Scale Integration (VLSI-SoC): Proceedings. ed. / Carolina Metzler; Giovanni De Micheli; Pierre-Emmanuel Gaillardon; Carlos Silva-Cardenas; Ricardo Reis. Institute of Electrical and Electronics Engineers Inc., 2019. p. 99-104 8920354 (International Conference on VLSI and System-on-Chip).

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

Gerlach, L, Paya-Vaya, G & Blume, H 2019, KAVUAKA: A Low Power Application Specific Hearing Aid Processor. in C Metzler, G De Micheli, P-E Gaillardon, C Silva-Cardenas & R Reis (eds), 2019 IFIP/IEEE 27th International Conference on Very Large Scale Integration (VLSI-SoC): Proceedings., 8920354, International Conference on VLSI and System-on-Chip, Institute of Electrical and Electronics Engineers Inc., pp. 99-104, 27th IFIP/IEEE International Conference on Very Large Scale Integration, VLSI-SoC 2019, Cuzco, Peru, 6 Oct 2019. https://doi.org/10.1109/VLSI-SoC.2019.8920354
Gerlach, L., Paya-Vaya, G., & Blume, H. (2019). KAVUAKA: A Low Power Application Specific Hearing Aid Processor. In C. Metzler, G. De Micheli, P.-E. Gaillardon, C. Silva-Cardenas, & R. Reis (Eds.), 2019 IFIP/IEEE 27th International Conference on Very Large Scale Integration (VLSI-SoC): Proceedings (pp. 99-104). Article 8920354 (International Conference on VLSI and System-on-Chip). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/VLSI-SoC.2019.8920354
Gerlach L, Paya-Vaya G, Blume H. KAVUAKA: A Low Power Application Specific Hearing Aid Processor. In Metzler C, De Micheli G, Gaillardon PE, Silva-Cardenas C, Reis R, editors, 2019 IFIP/IEEE 27th International Conference on Very Large Scale Integration (VLSI-SoC): Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. p. 99-104. 8920354. (International Conference on VLSI and System-on-Chip). doi: 10.1109/VLSI-SoC.2019.8920354
Gerlach, Lukas ; Paya-Vaya, Guillermo ; Blume, Holger. / KAVUAKA : A Low Power Application Specific Hearing Aid Processor. 2019 IFIP/IEEE 27th International Conference on Very Large Scale Integration (VLSI-SoC): Proceedings. editor / Carolina Metzler ; Giovanni De Micheli ; Pierre-Emmanuel Gaillardon ; Carlos Silva-Cardenas ; Ricardo Reis. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 99-104 (International Conference on VLSI and System-on-Chip).
Download
@inproceedings{265b377668014c64ade3b6b3ddb714a2,
title = "KAVUAKA: A Low Power Application Specific Hearing Aid Processor",
abstract = "The integration of application specific instruction set processors (ASIPs) in hearing aids requires various architectural customizations and software-side optimizations in order to meet the stringent power consumption constraints and processing performance demands. This paper presents the KAVUAKA application specific hearing aid processor and its ASIC integration as a system on chip (SoC). The final system contains four KAVUAKA processor cores and ten co-processors. Each of these processors and co-processors were individually customized and differ in their data path width. The processors are organized in two clusters, which share memories, an audio interface, co-processors and a serial interface. With this system, different hearing aid systems are evaluated in terms of performance, power and area by activating different processor and co-processor combinations. A 40 nm low power technology was used to build this research hearing aid system. The die size is 3.6 mm 2 with less than 1 mm 2 per core. The measured average power consumption is less than 1 mW per core.",
keywords = "asic, asip, hearing aid, low-power, processor, system on chip",
author = "Lukas Gerlach and Guillermo Paya-Vaya and Holger Blume",
note = "Funding information: This work was funded by the Deutsche Forschungsgemein-schaft (DFG, German Research Foundation) under Germany{\textquoteright}s Excellence Strategy – EXC 2177/1 – Project ID 390895286.; 27th IFIP/IEEE International Conference on Very Large Scale Integration, VLSI-SoC 2019 ; Conference date: 06-10-2019 Through 09-10-2019",
year = "2019",
month = oct,
doi = "10.1109/VLSI-SoC.2019.8920354",
language = "English",
isbn = "978-1-7281-3916-6",
series = "International Conference on VLSI and System-on-Chip",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "99--104",
editor = "Carolina Metzler and {De Micheli}, Giovanni and Pierre-Emmanuel Gaillardon and Carlos Silva-Cardenas and Ricardo Reis",
booktitle = "2019 IFIP/IEEE 27th International Conference on Very Large Scale Integration (VLSI-SoC)",
address = "United States",

}

Download

TY - GEN

T1 - KAVUAKA

T2 - 27th IFIP/IEEE International Conference on Very Large Scale Integration, VLSI-SoC 2019

AU - Gerlach, Lukas

AU - Paya-Vaya, Guillermo

AU - Blume, Holger

N1 - Funding information: This work was funded by the Deutsche Forschungsgemein-schaft (DFG, German Research Foundation) under Germany’s Excellence Strategy – EXC 2177/1 – Project ID 390895286.

PY - 2019/10

Y1 - 2019/10

N2 - The integration of application specific instruction set processors (ASIPs) in hearing aids requires various architectural customizations and software-side optimizations in order to meet the stringent power consumption constraints and processing performance demands. This paper presents the KAVUAKA application specific hearing aid processor and its ASIC integration as a system on chip (SoC). The final system contains four KAVUAKA processor cores and ten co-processors. Each of these processors and co-processors were individually customized and differ in their data path width. The processors are organized in two clusters, which share memories, an audio interface, co-processors and a serial interface. With this system, different hearing aid systems are evaluated in terms of performance, power and area by activating different processor and co-processor combinations. A 40 nm low power technology was used to build this research hearing aid system. The die size is 3.6 mm 2 with less than 1 mm 2 per core. The measured average power consumption is less than 1 mW per core.

AB - The integration of application specific instruction set processors (ASIPs) in hearing aids requires various architectural customizations and software-side optimizations in order to meet the stringent power consumption constraints and processing performance demands. This paper presents the KAVUAKA application specific hearing aid processor and its ASIC integration as a system on chip (SoC). The final system contains four KAVUAKA processor cores and ten co-processors. Each of these processors and co-processors were individually customized and differ in their data path width. The processors are organized in two clusters, which share memories, an audio interface, co-processors and a serial interface. With this system, different hearing aid systems are evaluated in terms of performance, power and area by activating different processor and co-processor combinations. A 40 nm low power technology was used to build this research hearing aid system. The die size is 3.6 mm 2 with less than 1 mm 2 per core. The measured average power consumption is less than 1 mW per core.

KW - asic

KW - asip

KW - hearing aid

KW - low-power

KW - processor

KW - system on chip

UR - http://www.scopus.com/inward/record.url?scp=85076823916&partnerID=8YFLogxK

U2 - 10.1109/VLSI-SoC.2019.8920354

DO - 10.1109/VLSI-SoC.2019.8920354

M3 - Conference contribution

AN - SCOPUS:85076823916

SN - 978-1-7281-3916-6

T3 - International Conference on VLSI and System-on-Chip

SP - 99

EP - 104

BT - 2019 IFIP/IEEE 27th International Conference on Very Large Scale Integration (VLSI-SoC)

A2 - Metzler, Carolina

A2 - De Micheli, Giovanni

A2 - Gaillardon, Pierre-Emmanuel

A2 - Silva-Cardenas, Carlos

A2 - Reis, Ricardo

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 6 October 2019 through 9 October 2019

ER -

By the same author(s)