Feasibility analysis of real-time physical modeling using WaveCore processor technology on FPGA

Martinus Johannes Wilhelmina Verstraelen, Florian Pfeifle, Rolf Bader

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademic

Abstract

WaveCore is a scalable many-core processor technology. This technology is specifically developed and optimized for real-time acoustical modeling applications. The programmable WaveCore soft-core processor is silicon-technology independent and hence can be targeted to ASIC or FPGA technologies. The WaveCore programming methodology is based on dataflow principles and the abstraction level of the programming language is close to the mathematical structure of for instance finite difference timedomain schemes. The instruction set of the processor inherently supports delay-lines and data-flow graph constructs. Hence, the processor technology is well suitable to capture both digital waveguide as well as finite-difference oriented algorithm descriptions. We have analysed the feasibility of mapping 1D and 2D finite-difference models onto this processor technology, where we took Matlab reference code as a starting point. We analyzed the scalability and mapping characteristics of such models on the WaveCore architecture. Furthermore we investigated the composability of such models, which is an important property to enable the creation and mapping of complete musical instrument models. One part of the composability analysis has been to combine digital waveguide (FDN reverberation model) with finite-difference time-domain models (primitive six-string instrument model). The mapping experiments show a high efficiency in terms of FPGA utilization, combined with a programming methodology that matches in a transparent way with the mathematical abstraction level of the application domain. We used a standard FPGA board to get full-circle confidence of the carried-out analysis. The WaveCore compiler and simulator results have shown the scalability of the processor technology to support large models.
Original languageUndefined
Title of host publicationProceedings of the Third Vienna Talk on Music Acoustics
Place of PublicationVienna, Austria
PublisherInstitute of Musical Acoustics (Wiener Klangstil)
Pages273-280
Number of pages8
ISBN (Print)2413-6689
Publication statusPublished - 18 Sep 2015

Publication series

Name
PublisherVienna: Institute of Musical Acoustics (Wiener Klangstil)
ISSN (Print)2413-6689

Keywords

  • processor technology
  • EWI-26470
  • FDTD
  • FPGA
  • IR-100363
  • Acoustics
  • Modeling
  • METIS-316821
  • Real Time

Cite this

Verstraelen, M. J. W., Pfeifle, F., & Bader, R. (2015). Feasibility analysis of real-time physical modeling using WaveCore processor technology on FPGA. In Proceedings of the Third Vienna Talk on Music Acoustics (pp. 273-280). Vienna, Austria: Institute of Musical Acoustics (Wiener Klangstil).
Verstraelen, Martinus Johannes Wilhelmina ; Pfeifle, Florian ; Bader, Rolf. / Feasibility analysis of real-time physical modeling using WaveCore processor technology on FPGA. Proceedings of the Third Vienna Talk on Music Acoustics. Vienna, Austria : Institute of Musical Acoustics (Wiener Klangstil), 2015. pp. 273-280
@inproceedings{64845226060f4f92ac83d13196457b58,
title = "Feasibility analysis of real-time physical modeling using WaveCore processor technology on FPGA",
abstract = "WaveCore is a scalable many-core processor technology. This technology is specifically developed and optimized for real-time acoustical modeling applications. The programmable WaveCore soft-core processor is silicon-technology independent and hence can be targeted to ASIC or FPGA technologies. The WaveCore programming methodology is based on dataflow principles and the abstraction level of the programming language is close to the mathematical structure of for instance finite difference timedomain schemes. The instruction set of the processor inherently supports delay-lines and data-flow graph constructs. Hence, the processor technology is well suitable to capture both digital waveguide as well as finite-difference oriented algorithm descriptions. We have analysed the feasibility of mapping 1D and 2D finite-difference models onto this processor technology, where we took Matlab reference code as a starting point. We analyzed the scalability and mapping characteristics of such models on the WaveCore architecture. Furthermore we investigated the composability of such models, which is an important property to enable the creation and mapping of complete musical instrument models. One part of the composability analysis has been to combine digital waveguide (FDN reverberation model) with finite-difference time-domain models (primitive six-string instrument model). The mapping experiments show a high efficiency in terms of FPGA utilization, combined with a programming methodology that matches in a transparent way with the mathematical abstraction level of the application domain. We used a standard FPGA board to get full-circle confidence of the carried-out analysis. The WaveCore compiler and simulator results have shown the scalability of the processor technology to support large models.",
keywords = "processor technology, EWI-26470, FDTD, FPGA, IR-100363, Acoustics, Modeling, METIS-316821, Real Time",
author = "Verstraelen, {Martinus Johannes Wilhelmina} and Florian Pfeifle and Rolf Bader",
note = "Proceedings page: http://viennatalk2015.mdw.ac.at/?page_id=13001",
year = "2015",
month = "9",
day = "18",
language = "Undefined",
isbn = "2413-6689",
publisher = "Institute of Musical Acoustics (Wiener Klangstil)",
pages = "273--280",
booktitle = "Proceedings of the Third Vienna Talk on Music Acoustics",

}

Verstraelen, MJW, Pfeifle, F & Bader, R 2015, Feasibility analysis of real-time physical modeling using WaveCore processor technology on FPGA. in Proceedings of the Third Vienna Talk on Music Acoustics. Institute of Musical Acoustics (Wiener Klangstil), Vienna, Austria, pp. 273-280.

Feasibility analysis of real-time physical modeling using WaveCore processor technology on FPGA. / Verstraelen, Martinus Johannes Wilhelmina; Pfeifle, Florian; Bader, Rolf.

Proceedings of the Third Vienna Talk on Music Acoustics. Vienna, Austria : Institute of Musical Acoustics (Wiener Klangstil), 2015. p. 273-280.

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademic

TY - GEN

T1 - Feasibility analysis of real-time physical modeling using WaveCore processor technology on FPGA

AU - Verstraelen, Martinus Johannes Wilhelmina

AU - Pfeifle, Florian

AU - Bader, Rolf

N1 - Proceedings page: http://viennatalk2015.mdw.ac.at/?page_id=13001

PY - 2015/9/18

Y1 - 2015/9/18

N2 - WaveCore is a scalable many-core processor technology. This technology is specifically developed and optimized for real-time acoustical modeling applications. The programmable WaveCore soft-core processor is silicon-technology independent and hence can be targeted to ASIC or FPGA technologies. The WaveCore programming methodology is based on dataflow principles and the abstraction level of the programming language is close to the mathematical structure of for instance finite difference timedomain schemes. The instruction set of the processor inherently supports delay-lines and data-flow graph constructs. Hence, the processor technology is well suitable to capture both digital waveguide as well as finite-difference oriented algorithm descriptions. We have analysed the feasibility of mapping 1D and 2D finite-difference models onto this processor technology, where we took Matlab reference code as a starting point. We analyzed the scalability and mapping characteristics of such models on the WaveCore architecture. Furthermore we investigated the composability of such models, which is an important property to enable the creation and mapping of complete musical instrument models. One part of the composability analysis has been to combine digital waveguide (FDN reverberation model) with finite-difference time-domain models (primitive six-string instrument model). The mapping experiments show a high efficiency in terms of FPGA utilization, combined with a programming methodology that matches in a transparent way with the mathematical abstraction level of the application domain. We used a standard FPGA board to get full-circle confidence of the carried-out analysis. The WaveCore compiler and simulator results have shown the scalability of the processor technology to support large models.

AB - WaveCore is a scalable many-core processor technology. This technology is specifically developed and optimized for real-time acoustical modeling applications. The programmable WaveCore soft-core processor is silicon-technology independent and hence can be targeted to ASIC or FPGA technologies. The WaveCore programming methodology is based on dataflow principles and the abstraction level of the programming language is close to the mathematical structure of for instance finite difference timedomain schemes. The instruction set of the processor inherently supports delay-lines and data-flow graph constructs. Hence, the processor technology is well suitable to capture both digital waveguide as well as finite-difference oriented algorithm descriptions. We have analysed the feasibility of mapping 1D and 2D finite-difference models onto this processor technology, where we took Matlab reference code as a starting point. We analyzed the scalability and mapping characteristics of such models on the WaveCore architecture. Furthermore we investigated the composability of such models, which is an important property to enable the creation and mapping of complete musical instrument models. One part of the composability analysis has been to combine digital waveguide (FDN reverberation model) with finite-difference time-domain models (primitive six-string instrument model). The mapping experiments show a high efficiency in terms of FPGA utilization, combined with a programming methodology that matches in a transparent way with the mathematical abstraction level of the application domain. We used a standard FPGA board to get full-circle confidence of the carried-out analysis. The WaveCore compiler and simulator results have shown the scalability of the processor technology to support large models.

KW - processor technology

KW - EWI-26470

KW - FDTD

KW - FPGA

KW - IR-100363

KW - Acoustics

KW - Modeling

KW - METIS-316821

KW - Real Time

M3 - Conference contribution

SN - 2413-6689

SP - 273

EP - 280

BT - Proceedings of the Third Vienna Talk on Music Acoustics

PB - Institute of Musical Acoustics (Wiener Klangstil)

CY - Vienna, Austria

ER -

Verstraelen MJW, Pfeifle F, Bader R. Feasibility analysis of real-time physical modeling using WaveCore processor technology on FPGA. In Proceedings of the Third Vienna Talk on Music Acoustics. Vienna, Austria: Institute of Musical Acoustics (Wiener Klangstil). 2015. p. 273-280