Throughput-fairness tradeoff in best effort flow control for on-chip architectures

Fahimeh Jafari, Mohammad S. Talebi, Mohammad H. Yaghmaee, Ahmad Khonsari, Mohamed Ould-Khaoua

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

2 Citations (Scopus)

Abstract

We consider two flow control schemes for Best Effort traffic in on-chip architectures, which can be deemed as the solutions to the boundary extremes of a class of utility maximization problem. At one extreme, we consider the so-called Rate-Sum flow control scheme, which aims at improving the performance of the underlying system by roughly maximizing throughput while satisfying capacity constraints. At the other extreme, we deem the Max-Min flow control, whose concern is to maintain Max-Min fairness in rate allocation by fairly sacrificing the throughput. We then elaborate our argument through a weighting mechanism in order to achieve a balance between the orthogonal goals of performance and fairness. Moreover, we investigate the implementation facets of the presented flow control schemes in on-chip architectures. Finally, we validate the proposed flow control schemes and the subsequent arguments through extensive simulation experiments.

Original languageEnglish
Title of host publicationIPDPS 2009 - Proceedings of the 2009 IEEE International Parallel and Distributed Processing Symposium
DOIs
Publication statusPublished - 2009
Event23rd IEEE International Parallel and Distributed Processing Symposium, IPDPS 2009 - Rome, Italy
Duration: May 23 2009May 29 2009

Other

Other23rd IEEE International Parallel and Distributed Processing Symposium, IPDPS 2009
CountryItaly
CityRome
Period5/23/095/29/09

Fingerprint

Flow control
Throughput
Experiments

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Hardware and Architecture
  • Software

Cite this

Jafari, F., Talebi, M. S., Yaghmaee, M. H., Khonsari, A., & Ould-Khaoua, M. (2009). Throughput-fairness tradeoff in best effort flow control for on-chip architectures. In IPDPS 2009 - Proceedings of the 2009 IEEE International Parallel and Distributed Processing Symposium [5161186] https://doi.org/10.1109/IPDPS.2009.5161186

Throughput-fairness tradeoff in best effort flow control for on-chip architectures. / Jafari, Fahimeh; Talebi, Mohammad S.; Yaghmaee, Mohammad H.; Khonsari, Ahmad; Ould-Khaoua, Mohamed.

IPDPS 2009 - Proceedings of the 2009 IEEE International Parallel and Distributed Processing Symposium. 2009. 5161186.

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

Jafari, F, Talebi, MS, Yaghmaee, MH, Khonsari, A & Ould-Khaoua, M 2009, Throughput-fairness tradeoff in best effort flow control for on-chip architectures. in IPDPS 2009 - Proceedings of the 2009 IEEE International Parallel and Distributed Processing Symposium., 5161186, 23rd IEEE International Parallel and Distributed Processing Symposium, IPDPS 2009, Rome, Italy, 5/23/09. https://doi.org/10.1109/IPDPS.2009.5161186
Jafari F, Talebi MS, Yaghmaee MH, Khonsari A, Ould-Khaoua M. Throughput-fairness tradeoff in best effort flow control for on-chip architectures. In IPDPS 2009 - Proceedings of the 2009 IEEE International Parallel and Distributed Processing Symposium. 2009. 5161186 https://doi.org/10.1109/IPDPS.2009.5161186
Jafari, Fahimeh ; Talebi, Mohammad S. ; Yaghmaee, Mohammad H. ; Khonsari, Ahmad ; Ould-Khaoua, Mohamed. / Throughput-fairness tradeoff in best effort flow control for on-chip architectures. IPDPS 2009 - Proceedings of the 2009 IEEE International Parallel and Distributed Processing Symposium. 2009.
@inproceedings{0d6006cc8c634310abae05ef68e7fb06,
title = "Throughput-fairness tradeoff in best effort flow control for on-chip architectures",
abstract = "We consider two flow control schemes for Best Effort traffic in on-chip architectures, which can be deemed as the solutions to the boundary extremes of a class of utility maximization problem. At one extreme, we consider the so-called Rate-Sum flow control scheme, which aims at improving the performance of the underlying system by roughly maximizing throughput while satisfying capacity constraints. At the other extreme, we deem the Max-Min flow control, whose concern is to maintain Max-Min fairness in rate allocation by fairly sacrificing the throughput. We then elaborate our argument through a weighting mechanism in order to achieve a balance between the orthogonal goals of performance and fairness. Moreover, we investigate the implementation facets of the presented flow control schemes in on-chip architectures. Finally, we validate the proposed flow control schemes and the subsequent arguments through extensive simulation experiments.",
author = "Fahimeh Jafari and Talebi, {Mohammad S.} and Yaghmaee, {Mohammad H.} and Ahmad Khonsari and Mohamed Ould-Khaoua",
year = "2009",
doi = "10.1109/IPDPS.2009.5161186",
language = "English",
isbn = "9781424437504",
booktitle = "IPDPS 2009 - Proceedings of the 2009 IEEE International Parallel and Distributed Processing Symposium",

}

TY - GEN

T1 - Throughput-fairness tradeoff in best effort flow control for on-chip architectures

AU - Jafari, Fahimeh

AU - Talebi, Mohammad S.

AU - Yaghmaee, Mohammad H.

AU - Khonsari, Ahmad

AU - Ould-Khaoua, Mohamed

PY - 2009

Y1 - 2009

N2 - We consider two flow control schemes for Best Effort traffic in on-chip architectures, which can be deemed as the solutions to the boundary extremes of a class of utility maximization problem. At one extreme, we consider the so-called Rate-Sum flow control scheme, which aims at improving the performance of the underlying system by roughly maximizing throughput while satisfying capacity constraints. At the other extreme, we deem the Max-Min flow control, whose concern is to maintain Max-Min fairness in rate allocation by fairly sacrificing the throughput. We then elaborate our argument through a weighting mechanism in order to achieve a balance between the orthogonal goals of performance and fairness. Moreover, we investigate the implementation facets of the presented flow control schemes in on-chip architectures. Finally, we validate the proposed flow control schemes and the subsequent arguments through extensive simulation experiments.

AB - We consider two flow control schemes for Best Effort traffic in on-chip architectures, which can be deemed as the solutions to the boundary extremes of a class of utility maximization problem. At one extreme, we consider the so-called Rate-Sum flow control scheme, which aims at improving the performance of the underlying system by roughly maximizing throughput while satisfying capacity constraints. At the other extreme, we deem the Max-Min flow control, whose concern is to maintain Max-Min fairness in rate allocation by fairly sacrificing the throughput. We then elaborate our argument through a weighting mechanism in order to achieve a balance between the orthogonal goals of performance and fairness. Moreover, we investigate the implementation facets of the presented flow control schemes in on-chip architectures. Finally, we validate the proposed flow control schemes and the subsequent arguments through extensive simulation experiments.

UR - http://www.scopus.com/inward/record.url?scp=70449810244&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70449810244&partnerID=8YFLogxK

U2 - 10.1109/IPDPS.2009.5161186

DO - 10.1109/IPDPS.2009.5161186

M3 - Conference contribution

AN - SCOPUS:70449810244

SN - 9781424437504

BT - IPDPS 2009 - Proceedings of the 2009 IEEE International Parallel and Distributed Processing Symposium

ER -