Resource estimation and task scheduling for multithreaded reconfigurable architectures

Arvind Sudarsanam, Mayur Srinivasan, Sethuraman Panchanathan

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

13 Citations (Scopus)

Abstract

Reconfigurable computing is an emerging paradigm of research that offers cost-effective solutions for computationally intensive applications through hardware reuse. There is a growing need in this domain for techniques to exploit parallelism inherent in the target application and to schedule the parallelized application. This paper proposes a method to estimate the optimal number of resources through critical path analysis while keeping resource utilization near optimal. We also propose a novel algorithm to optimally schedule the parallel threads of execution in linear time. Our algorithm is based on the idea of enhanced Partial Critical Path (ePCP) and handles memory latencies and reconfiguration overheads. Results obtained show the effectiveness of our approach over other critical path based methods.

Original languageEnglish (US)
Title of host publicationProceedings - Tenth International Conference on Parallel and Distributed Systems (ICPADS 2004)
EditorsN.F. Tzeng
Pages323-330
Number of pages8
Volume10
DOIs
StatePublished - 2004
EventProceedings - Tenth International Conference on Parallel and Distributed Systems (ICPADS 2004) - Newport Beach, CA, United States
Duration: Jul 7 2004Jul 9 2004

Other

OtherProceedings - Tenth International Conference on Parallel and Distributed Systems (ICPADS 2004)
CountryUnited States
CityNewport Beach, CA
Period7/7/047/9/04

Fingerprint

Reconfigurable architectures
Scheduling
Critical path analysis
Hardware
Data storage equipment
Costs

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Sudarsanam, A., Srinivasan, M., & Panchanathan, S. (2004). Resource estimation and task scheduling for multithreaded reconfigurable architectures. In N. F. Tzeng (Ed.), Proceedings - Tenth International Conference on Parallel and Distributed Systems (ICPADS 2004) (Vol. 10, pp. 323-330) https://doi.org/10.1109/ICPADS.2004.1316111

Resource estimation and task scheduling for multithreaded reconfigurable architectures. / Sudarsanam, Arvind; Srinivasan, Mayur; Panchanathan, Sethuraman.

Proceedings - Tenth International Conference on Parallel and Distributed Systems (ICPADS 2004). ed. / N.F. Tzeng. Vol. 10 2004. p. 323-330.

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

Sudarsanam, A, Srinivasan, M & Panchanathan, S 2004, Resource estimation and task scheduling for multithreaded reconfigurable architectures. in NF Tzeng (ed.), Proceedings - Tenth International Conference on Parallel and Distributed Systems (ICPADS 2004). vol. 10, pp. 323-330, Proceedings - Tenth International Conference on Parallel and Distributed Systems (ICPADS 2004), Newport Beach, CA, United States, 7/7/04. https://doi.org/10.1109/ICPADS.2004.1316111
Sudarsanam A, Srinivasan M, Panchanathan S. Resource estimation and task scheduling for multithreaded reconfigurable architectures. In Tzeng NF, editor, Proceedings - Tenth International Conference on Parallel and Distributed Systems (ICPADS 2004). Vol. 10. 2004. p. 323-330 https://doi.org/10.1109/ICPADS.2004.1316111
Sudarsanam, Arvind ; Srinivasan, Mayur ; Panchanathan, Sethuraman. / Resource estimation and task scheduling for multithreaded reconfigurable architectures. Proceedings - Tenth International Conference on Parallel and Distributed Systems (ICPADS 2004). editor / N.F. Tzeng. Vol. 10 2004. pp. 323-330
@inproceedings{360a2584c0d84932ac2772b6345e7fc7,
title = "Resource estimation and task scheduling for multithreaded reconfigurable architectures",
abstract = "Reconfigurable computing is an emerging paradigm of research that offers cost-effective solutions for computationally intensive applications through hardware reuse. There is a growing need in this domain for techniques to exploit parallelism inherent in the target application and to schedule the parallelized application. This paper proposes a method to estimate the optimal number of resources through critical path analysis while keeping resource utilization near optimal. We also propose a novel algorithm to optimally schedule the parallel threads of execution in linear time. Our algorithm is based on the idea of enhanced Partial Critical Path (ePCP) and handles memory latencies and reconfiguration overheads. Results obtained show the effectiveness of our approach over other critical path based methods.",
author = "Arvind Sudarsanam and Mayur Srinivasan and Sethuraman Panchanathan",
year = "2004",
doi = "10.1109/ICPADS.2004.1316111",
language = "English (US)",
volume = "10",
pages = "323--330",
editor = "N.F. Tzeng",
booktitle = "Proceedings - Tenth International Conference on Parallel and Distributed Systems (ICPADS 2004)",

}

TY - GEN

T1 - Resource estimation and task scheduling for multithreaded reconfigurable architectures

AU - Sudarsanam, Arvind

AU - Srinivasan, Mayur

AU - Panchanathan, Sethuraman

PY - 2004

Y1 - 2004

N2 - Reconfigurable computing is an emerging paradigm of research that offers cost-effective solutions for computationally intensive applications through hardware reuse. There is a growing need in this domain for techniques to exploit parallelism inherent in the target application and to schedule the parallelized application. This paper proposes a method to estimate the optimal number of resources through critical path analysis while keeping resource utilization near optimal. We also propose a novel algorithm to optimally schedule the parallel threads of execution in linear time. Our algorithm is based on the idea of enhanced Partial Critical Path (ePCP) and handles memory latencies and reconfiguration overheads. Results obtained show the effectiveness of our approach over other critical path based methods.

AB - Reconfigurable computing is an emerging paradigm of research that offers cost-effective solutions for computationally intensive applications through hardware reuse. There is a growing need in this domain for techniques to exploit parallelism inherent in the target application and to schedule the parallelized application. This paper proposes a method to estimate the optimal number of resources through critical path analysis while keeping resource utilization near optimal. We also propose a novel algorithm to optimally schedule the parallel threads of execution in linear time. Our algorithm is based on the idea of enhanced Partial Critical Path (ePCP) and handles memory latencies and reconfiguration overheads. Results obtained show the effectiveness of our approach over other critical path based methods.

UR - http://www.scopus.com/inward/record.url?scp=4544342373&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=4544342373&partnerID=8YFLogxK

U2 - 10.1109/ICPADS.2004.1316111

DO - 10.1109/ICPADS.2004.1316111

M3 - Conference contribution

AN - SCOPUS:4544342373

VL - 10

SP - 323

EP - 330

BT - Proceedings - Tenth International Conference on Parallel and Distributed Systems (ICPADS 2004)

A2 - Tzeng, N.F.

ER -