Design space exploration of a particle filter using higher-0rder functions

Rinse Wester, Jan Kuper

Abstract

This paper presents a design space exploration methodology based on higher-order functions to facilitate the tradeoff between execution time and area usage on FPGAs. Higher-order function are transformed, resulting in parameterized nodes where the amount of parallelism and thereby performance, can be controlled. For composition and scheduling of operations, dataflow principles are used. To show the validity of the approach, a particle filter has been transformed and synthesized for FPGA. The resulting architecture is parameterizable and achieves good performance.
Original languageUndefined
Title of host publicationReconfigurable Computing: Architectures, Tools, and Applications
Place of PublicationLondon
PublisherSpringer
Pages219-226
Number of pages8
ISBN (Print)978-3-319-05959-4
DOIs
StatePublished - 2014

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Verlag
Number8405
Volume8405
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Fingerprint

Field programmable gate arrays (FPGA)
Scheduling
Chemical analysis

Keywords

  • EWI-24700
  • Tradeoff
  • IR-90642
  • Higher-order functions
  • METIS-305870
  • Particle filter

Cite this

Wester, R., & Kuper, J. (2014). Design space exploration of a particle filter using higher-0rder functions. In Reconfigurable Computing: Architectures, Tools, and Applications (pp. 219-226). (Lecture Notes in Computer Science; Vol. 8405, No. 8405). London: Springer. DOI: 10.1007/978-3-319-05960-0_21

Wester, Rinse; Kuper, Jan / Design space exploration of a particle filter using higher-0rder functions.

Reconfigurable Computing: Architectures, Tools, and Applications. London : Springer, 2014. p. 219-226 (Lecture Notes in Computer Science; Vol. 8405, No. 8405).

Research output: Scientific - peer-review › Chapter

@inbook{b0d28075793f407684942d1862b46e7c,
title = "Design space exploration of a particle filter using higher-0rder functions",
abstract = "This paper presents a design space exploration methodology based on higher-order functions to facilitate the tradeoff between execution time and area usage on FPGAs. Higher-order function are transformed, resulting in parameterized nodes where the amount of parallelism and thereby performance, can be controlled. For composition and scheduling of operations, dataflow principles are used. To show the validity of the approach, a particle filter has been transformed and synthesized for FPGA. The resulting architecture is parameterizable and achieves good performance.",
keywords = "EWI-24700, Tradeoff, IR-90642, Higher-order functions, METIS-305870, Particle filter",
author = "Rinse Wester and Jan Kuper",
note = "10.1007/978-3-319-05960-0_21",
year = "2014",
doi = "10.1007/978-3-319-05960-0_21",
isbn = "978-3-319-05959-4",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
number = "8405",
pages = "219--226",
booktitle = "Reconfigurable Computing: Architectures, Tools, and Applications",

}

Wester, R & Kuper, J 2014, Design space exploration of a particle filter using higher-0rder functions. in Reconfigurable Computing: Architectures, Tools, and Applications. Lecture Notes in Computer Science, no. 8405, vol. 8405, Springer, London, pp. 219-226. DOI: 10.1007/978-3-319-05960-0_21

Design space exploration of a particle filter using higher-0rder functions. / Wester, Rinse; Kuper, Jan.

Reconfigurable Computing: Architectures, Tools, and Applications. London : Springer, 2014. p. 219-226 (Lecture Notes in Computer Science; Vol. 8405, No. 8405).

Research output: Scientific - peer-review › Chapter

TY - CHAP

T1 - Design space exploration of a particle filter using higher-0rder functions

AU - Wester,Rinse

AU - Kuper,Jan

N1 - 10.1007/978-3-319-05960-0_21

PY - 2014

Y1 - 2014

N2 - This paper presents a design space exploration methodology based on higher-order functions to facilitate the tradeoff between execution time and area usage on FPGAs. Higher-order function are transformed, resulting in parameterized nodes where the amount of parallelism and thereby performance, can be controlled. For composition and scheduling of operations, dataflow principles are used. To show the validity of the approach, a particle filter has been transformed and synthesized for FPGA. The resulting architecture is parameterizable and achieves good performance.

AB - This paper presents a design space exploration methodology based on higher-order functions to facilitate the tradeoff between execution time and area usage on FPGAs. Higher-order function are transformed, resulting in parameterized nodes where the amount of parallelism and thereby performance, can be controlled. For composition and scheduling of operations, dataflow principles are used. To show the validity of the approach, a particle filter has been transformed and synthesized for FPGA. The resulting architecture is parameterizable and achieves good performance.

KW - EWI-24700

KW - Tradeoff

KW - IR-90642

KW - Higher-order functions

KW - METIS-305870

KW - Particle filter

U2 - 10.1007/978-3-319-05960-0_21

DO - 10.1007/978-3-319-05960-0_21

M3 - Chapter

SN - 978-3-319-05959-4

T3 - Lecture Notes in Computer Science

SP - 219

EP - 226

BT - Reconfigurable Computing: Architectures, Tools, and Applications

PB - Springer

ER -

Wester R, Kuper J. Design space exploration of a particle filter using higher-0rder functions. In Reconfigurable Computing: Architectures, Tools, and Applications. London: Springer. 2014. p. 219-226. (Lecture Notes in Computer Science; 8405). Available from, DOI: 10.1007/978-3-319-05960-0_21

Access to Document