Optimisation of extended generalised fat tree topologies

Adamantini Peratikou; Mo Adda

doi:10.1007/978-3-319-05209-0_7

Optimisation of extended generalised fat tree topologies

Adamantini Peratikou, Mo Adda

School of Computing

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

269 Downloads (Pure)

Abstract

Extended generalised fat tree (XGFT) are interconnection networks with bidirectional multistage properties, (BMIN) which can be extended, or scaled to accommodate different system sizes and requirements. However, these extended topologies do not address power consumption and traffic constraints. In this paper, we extract a sub-set of the generalised fat tree topologies that are power consumption and performance aware. We called this sub-set optimised OXGFT. The cost which is proportional to the relative power is the objective function that is minimised based on the traffic constraints to maintain a lower delay and a higher throughput. The simulation results show that the extracted OXGFT topologies perform well under various load conditions.

Original language	English
Title of host publication	Distributed computer and communication networks
Subtitle of host publication	17th international conference, DCCN 2013, Moscow, Russia, October 7-10, 2013. revised selected papers
Editors	Vladimir Vishnevsky, Dmitry Kozyrev, Andrey Larionov
Place of Publication	Heidelberg
Publisher	Springer
Pages	82-90
ISBN (Electronic)	9783319052090
ISBN (Print)	9783319052083
DOIs	https://doi.org/10.1007/978-3-319-05209-0_7
Publication status	Published - 2014
Event	17th International Conference on Distributed Computer and Communication Networks - Moscow, Russian Federation Duration: 7 Oct 2013 → 10 Oct 2013

Publication series

Name	Communications in computer and information science
Publisher	Springer
Volume	279
ISSN (Print)	1865-0929

Conference

Conference	17th International Conference on Distributed Computer and Communication Networks
Country/Territory	Russian Federation
City	Moscow
Period	7/10/13 → 10/10/13

Access to Document

10.1007/978-3-319-05209-0_7

Optimisation of extended generalised fat tree topologiesAccepted author manuscript (Post-print), 10 MBLicence: Unspecified

3 Citations
2 Chapter (peer-reviewed)
1 Article

J-PMCRI: a methodology for inducing pre-pruned modular classification rules
Stahl, F., Bramer, M. & Adda, M., 2010, In: IFIP Advances in Information and Communication Technology. 331, p. 47-56 10 p.
Research output: Contribution to journal › Article › peer-review

File
219 Downloads (Pure)
Parallel rule induction with information theoretic pre-pruning
Stahl, F., Bramer, M. & Adda, M., 2010, Research and Development in Intelligent Systems XXVI. Ellis, R. & Petridis, M. (eds.). Springer, Vol. 4. p. 151-164 14 p.
Research output: Chapter in Book/Report/Conference proceeding › Chapter (peer-reviewed) › peer-review
PMCRI: a parallel modular classification rule induction framework
Stahl, F., Bramer, M. & Adda, M., 2009, Machine learning and data mining in pattern recognition: 6th international conference, MLDM 2009, Leipzig, Germany, July 23-25, 2009. proceedings. Perner, P. (ed.). 5632 ed. Berlin: Springer, Vol. 5632. p. 148-162 15 p. (Lecture notes in computer science; no. 5632).
Research output: Chapter in Book/Report/Conference proceeding › Chapter (peer-reviewed) › peer-review

File
210 Downloads (Pure)

Cite this

Peratikou, A., & Adda, M. (2014). Optimisation of extended generalised fat tree topologies. In V. Vishnevsky, D. Kozyrev, & A. Larionov (Eds.), Distributed computer and communication networks: 17th international conference, DCCN 2013, Moscow, Russia, October 7-10, 2013. revised selected papers (pp. 82-90). (Communications in computer and information science ; Vol. 279). Springer. https://doi.org/10.1007/978-3-319-05209-0_7

Peratikou, Adamantini ; Adda, Mo. / Optimisation of extended generalised fat tree topologies. Distributed computer and communication networks: 17th international conference, DCCN 2013, Moscow, Russia, October 7-10, 2013. revised selected papers. editor / Vladimir Vishnevsky ; Dmitry Kozyrev ; Andrey Larionov. Heidelberg : Springer, 2014. pp. 82-90 (Communications in computer and information science ).

@inproceedings{1dca3b5b3ba94249bc7225fe7383cee0,

title = "Optimisation of extended generalised fat tree topologies",

abstract = "Extended generalised fat tree (XGFT) are interconnection networks with bidirectional multistage properties, (BMIN) which can be extended, or scaled to accommodate different system sizes and requirements. However, these extended topologies do not address power consumption and traffic constraints. In this paper, we extract a sub-set of the generalised fat tree topologies that are power consumption and performance aware. We called this sub-set optimised OXGFT. The cost which is proportional to the relative power is the objective function that is minimised based on the traffic constraints to maintain a lower delay and a higher throughput. The simulation results show that the extracted OXGFT topologies perform well under various load conditions.",

author = "Adamantini Peratikou and Mo Adda",

year = "2014",

doi = "10.1007/978-3-319-05209-0\_7",

language = "English",

isbn = "9783319052083",

series = "Communications in computer and information science ",

publisher = "Springer",

pages = "82--90",

editor = "Vladimir Vishnevsky and Dmitry Kozyrev and Andrey Larionov",

booktitle = "Distributed computer and communication networks",

address = "Netherlands",

note = "17th International Conference on Distributed Computer and Communication Networks ; Conference date: 07-10-2013 Through 10-10-2013",

}

Peratikou, A & Adda, M 2014, Optimisation of extended generalised fat tree topologies. in V Vishnevsky, D Kozyrev & A Larionov (eds), Distributed computer and communication networks: 17th international conference, DCCN 2013, Moscow, Russia, October 7-10, 2013. revised selected papers. Communications in computer and information science , vol. 279, Springer, Heidelberg, pp. 82-90, 17th International Conference on Distributed Computer and Communication Networks, Moscow, Russian Federation, 7/10/13. https://doi.org/10.1007/978-3-319-05209-0_7

Optimisation of extended generalised fat tree topologies. / Peratikou, Adamantini; Adda, Mo.
Distributed computer and communication networks: 17th international conference, DCCN 2013, Moscow, Russia, October 7-10, 2013. revised selected papers. ed. / Vladimir Vishnevsky; Dmitry Kozyrev; Andrey Larionov. Heidelberg: Springer, 2014. p. 82-90 (Communications in computer and information science ; Vol. 279).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Optimisation of extended generalised fat tree topologies

AU - Peratikou, Adamantini

AU - Adda, Mo

PY - 2014

Y1 - 2014

N2 - Extended generalised fat tree (XGFT) are interconnection networks with bidirectional multistage properties, (BMIN) which can be extended, or scaled to accommodate different system sizes and requirements. However, these extended topologies do not address power consumption and traffic constraints. In this paper, we extract a sub-set of the generalised fat tree topologies that are power consumption and performance aware. We called this sub-set optimised OXGFT. The cost which is proportional to the relative power is the objective function that is minimised based on the traffic constraints to maintain a lower delay and a higher throughput. The simulation results show that the extracted OXGFT topologies perform well under various load conditions.

AB - Extended generalised fat tree (XGFT) are interconnection networks with bidirectional multistage properties, (BMIN) which can be extended, or scaled to accommodate different system sizes and requirements. However, these extended topologies do not address power consumption and traffic constraints. In this paper, we extract a sub-set of the generalised fat tree topologies that are power consumption and performance aware. We called this sub-set optimised OXGFT. The cost which is proportional to the relative power is the objective function that is minimised based on the traffic constraints to maintain a lower delay and a higher throughput. The simulation results show that the extracted OXGFT topologies perform well under various load conditions.

U2 - 10.1007/978-3-319-05209-0_7

DO - 10.1007/978-3-319-05209-0_7

M3 - Conference contribution

SN - 9783319052083

T3 - Communications in computer and information science

SP - 82

EP - 90

BT - Distributed computer and communication networks

A2 - Vishnevsky, Vladimir

A2 - Kozyrev, Dmitry

A2 - Larionov, Andrey

PB - Springer

CY - Heidelberg

T2 - 17th International Conference on Distributed Computer and Communication Networks

Y2 - 7 October 2013 through 10 October 2013

ER -

Peratikou A, Adda M. Optimisation of extended generalised fat tree topologies. In Vishnevsky V, Kozyrev D, Larionov A, editors, Distributed computer and communication networks: 17th international conference, DCCN 2013, Moscow, Russia, October 7-10, 2013. revised selected papers. Heidelberg: Springer. 2014. p. 82-90. (Communications in computer and information science ). doi: 10.1007/978-3-319-05209-0_7

Optimisation of extended generalised fat tree topologies

Abstract

Publication series

Conference

Access to Document

Fingerprint

Research output

J-PMCRI: a methodology for inducing pre-pruned modular classification rules

Parallel rule induction with information theoretic pre-pruning

PMCRI: a parallel modular classification rule induction framework

Cite this