Tampere University of Technology

TUTCRIS Research Portal

Integration of dataflow-based heterogeneous multiprocessor scheduling techniques in GNU radio

Research output: Contribution to journalArticleScientificpeer-review

Standard

Integration of dataflow-based heterogeneous multiprocessor scheduling techniques in GNU radio. / Zaki, George F.; Plishker, William; Bhattacharyya, Shuvra S.; Clancy, Charles; Kuykendall, John.

In: Journal of Signal Processing Systems, Vol. 70, No. 2, 02.2013, p. 177-191.

Research output: Contribution to journalArticleScientificpeer-review

Harvard

Zaki, GF, Plishker, W, Bhattacharyya, SS, Clancy, C & Kuykendall, J 2013, 'Integration of dataflow-based heterogeneous multiprocessor scheduling techniques in GNU radio', Journal of Signal Processing Systems, vol. 70, no. 2, pp. 177-191. https://doi.org/10.1007/s11265-012-0696-0

APA

Zaki, G. F., Plishker, W., Bhattacharyya, S. S., Clancy, C., & Kuykendall, J. (2013). Integration of dataflow-based heterogeneous multiprocessor scheduling techniques in GNU radio. Journal of Signal Processing Systems, 70(2), 177-191. https://doi.org/10.1007/s11265-012-0696-0

Vancouver

Zaki GF, Plishker W, Bhattacharyya SS, Clancy C, Kuykendall J. Integration of dataflow-based heterogeneous multiprocessor scheduling techniques in GNU radio. Journal of Signal Processing Systems. 2013 Feb;70(2):177-191. https://doi.org/10.1007/s11265-012-0696-0

Author

Zaki, George F. ; Plishker, William ; Bhattacharyya, Shuvra S. ; Clancy, Charles ; Kuykendall, John. / Integration of dataflow-based heterogeneous multiprocessor scheduling techniques in GNU radio. In: Journal of Signal Processing Systems. 2013 ; Vol. 70, No. 2. pp. 177-191.

Bibtex - Download

@article{f2ee77ba41c54eed87fd35df99c76d0d,
title = "Integration of dataflow-based heterogeneous multiprocessor scheduling techniques in GNU radio",
abstract = "As the variety of off-the-shelf processors expands, traditional implementation methods of systems for digital signal processing and communication are no longer adequate to achieve design objectives in a timely manner. There is a necessity for designers to easily track the changes in computing platforms, and apply them efficiently while reusing legacy code and optimized libraries that target specialized features in single processing units. In this context, we propose an integration workflow to schedule and implement Software Defined Radio (SDR) protocols that are developed using the GNU Radio environment on heterogeneous multiprocessor platforms. We show how to utilize Single Instruction Multiple Data (SIMD) units provided in Graphics Processing Units (GPUs) along with vector accelerators implemented in General Purpose Processors (GPPs). We augment a popular SDR framework (i.e, GNU Radio) with a library that seamlessly allows offloading of algorithm kernels mapped to the GPU without changing the original protocol description. Experimental results show how our approach can be used to efficiently explore design spaces for SDR system implementation, and examine the overhead of the integrated backend (software component) library.",
keywords = "Design methodology, GNU Radio, Graphic processor unit, Multiprocessor scheduling, Software defined radio",
author = "Zaki, {George F.} and William Plishker and Bhattacharyya, {Shuvra S.} and Charles Clancy and John Kuykendall",
year = "2013",
month = "2",
doi = "10.1007/s11265-012-0696-0",
language = "English",
volume = "70",
pages = "177--191",
journal = "Journal of Signal Processing Systems",
issn = "1939-8018",
publisher = "Springer Verlag",
number = "2",

}

RIS (suitable for import to EndNote) - Download

TY - JOUR

T1 - Integration of dataflow-based heterogeneous multiprocessor scheduling techniques in GNU radio

AU - Zaki, George F.

AU - Plishker, William

AU - Bhattacharyya, Shuvra S.

AU - Clancy, Charles

AU - Kuykendall, John

PY - 2013/2

Y1 - 2013/2

N2 - As the variety of off-the-shelf processors expands, traditional implementation methods of systems for digital signal processing and communication are no longer adequate to achieve design objectives in a timely manner. There is a necessity for designers to easily track the changes in computing platforms, and apply them efficiently while reusing legacy code and optimized libraries that target specialized features in single processing units. In this context, we propose an integration workflow to schedule and implement Software Defined Radio (SDR) protocols that are developed using the GNU Radio environment on heterogeneous multiprocessor platforms. We show how to utilize Single Instruction Multiple Data (SIMD) units provided in Graphics Processing Units (GPUs) along with vector accelerators implemented in General Purpose Processors (GPPs). We augment a popular SDR framework (i.e, GNU Radio) with a library that seamlessly allows offloading of algorithm kernels mapped to the GPU without changing the original protocol description. Experimental results show how our approach can be used to efficiently explore design spaces for SDR system implementation, and examine the overhead of the integrated backend (software component) library.

AB - As the variety of off-the-shelf processors expands, traditional implementation methods of systems for digital signal processing and communication are no longer adequate to achieve design objectives in a timely manner. There is a necessity for designers to easily track the changes in computing platforms, and apply them efficiently while reusing legacy code and optimized libraries that target specialized features in single processing units. In this context, we propose an integration workflow to schedule and implement Software Defined Radio (SDR) protocols that are developed using the GNU Radio environment on heterogeneous multiprocessor platforms. We show how to utilize Single Instruction Multiple Data (SIMD) units provided in Graphics Processing Units (GPUs) along with vector accelerators implemented in General Purpose Processors (GPPs). We augment a popular SDR framework (i.e, GNU Radio) with a library that seamlessly allows offloading of algorithm kernels mapped to the GPU without changing the original protocol description. Experimental results show how our approach can be used to efficiently explore design spaces for SDR system implementation, and examine the overhead of the integrated backend (software component) library.

KW - Design methodology

KW - GNU Radio

KW - Graphic processor unit

KW - Multiprocessor scheduling

KW - Software defined radio

UR - http://www.scopus.com/inward/record.url?scp=84892800816&partnerID=8YFLogxK

U2 - 10.1007/s11265-012-0696-0

DO - 10.1007/s11265-012-0696-0

M3 - Article

VL - 70

SP - 177

EP - 191

JO - Journal of Signal Processing Systems

JF - Journal of Signal Processing Systems

SN - 1939-8018

IS - 2

ER -