Network traffic exploration on a many-core computing platform: SpiNNaker real-time traffic visualiser

Gengting Liu; Patrick Camilleri; Stephen Furber; James Garside

doi:10.1109/PRIME.2015.7251376

Network traffic exploration on a many-core computing platform: SpiNNaker real-time traffic visualiser

Gengting Liu, Patrick Camilleri, Stephen Furber, James Garside

Advanced Processor Technology

Research output: Chapter in Book/Conference proceeding › Conference contribution › peer-review

Abstract

The performance of modern supercomputers is ever-increasing. Different kinds of massively parallel programs are written to maximally utilise the computing power provided by these many-core computing machines. However, this performance shrinks when network congestion occurs. SpiNNaker is an energy-efficient and highly parallel computing platform, which has built-in diagnostic hardware and congestion-aware adaptive routing. This paper describes the diagnostic technology available in SpiNNaker machines and presents a new software tool called SpiNNaker real-time traffic visualiser which adopts visualisation technology to explore the network traffic in SpiNNaker machines. This visualiser can assist application developers in detecting network traffic congestion with the provision of real-time configuration and data-logging functions.

Original language	English
Title of host publication	2015 11th Conference on Ph.D. Research in Microelectronics and Electronics, PRIME 2015
Publisher	IEEE
Pages	228-231
Number of pages	4
ISBN (Print)	9781479982295
DOIs	https://doi.org/10.1109/PRIME.2015.7251376
Publication status	Published - 9 Sept 2015
Event	11th Conference on Ph.D. Research in Microelectronics and Electronics, PRIME 2015 - Glasgow, United Kingdom Duration: 29 Jun 2015 → 2 Jul 2015

Conference

Conference	11th Conference on Ph.D. Research in Microelectronics and Electronics, PRIME 2015
Country/Territory	United Kingdom
City	Glasgow
Period	29/06/15 → 2/07/15

Keywords

Chip Multiprocessor
Network congestion
Network on Chip
Network traffic visualisation
SpiNNaker project

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/PRIME.2015.7251376

Cite this

@inproceedings{f6156c7adf674fdeb3fc4ee2a9189a60,

title = "Network traffic exploration on a many-core computing platform: SpiNNaker real-time traffic visualiser",

abstract = "The performance of modern supercomputers is ever-increasing. Different kinds of massively parallel programs are written to maximally utilise the computing power provided by these many-core computing machines. However, this performance shrinks when network congestion occurs. SpiNNaker is an energy-efficient and highly parallel computing platform, which has built-in diagnostic hardware and congestion-aware adaptive routing. This paper describes the diagnostic technology available in SpiNNaker machines and presents a new software tool called SpiNNaker real-time traffic visualiser which adopts visualisation technology to explore the network traffic in SpiNNaker machines. This visualiser can assist application developers in detecting network traffic congestion with the provision of real-time configuration and data-logging functions.",

keywords = "Chip Multiprocessor, Network congestion, Network on Chip, Network traffic visualisation, SpiNNaker project",

author = "Gengting Liu and Patrick Camilleri and Stephen Furber and James Garside",

year = "2015",

month = sep,

day = "9",

doi = "10.1109/PRIME.2015.7251376",

language = "English",

isbn = "9781479982295",

pages = "228--231",

booktitle = "2015 11th Conference on Ph.D. Research in Microelectronics and Electronics, PRIME 2015",

publisher = "IEEE",

address = "United States",

note = "11th Conference on Ph.D. Research in Microelectronics and Electronics, PRIME 2015 ; Conference date: 29-06-2015 Through 02-07-2015",

}

Liu, G, Camilleri, P, Furber, S & Garside, J 2015, Network traffic exploration on a many-core computing platform: SpiNNaker real-time traffic visualiser. in 2015 11th Conference on Ph.D. Research in Microelectronics and Electronics, PRIME 2015., 7251376, IEEE, pp. 228-231, 11th Conference on Ph.D. Research in Microelectronics and Electronics, PRIME 2015, Glasgow, United Kingdom, 29/06/15. https://doi.org/10.1109/PRIME.2015.7251376

Network traffic exploration on a many-core computing platform: SpiNNaker real-time traffic visualiser. / Liu, Gengting; Camilleri, Patrick; Furber, Stephen et al.
2015 11th Conference on Ph.D. Research in Microelectronics and Electronics, PRIME 2015. IEEE, 2015. p. 228-231 7251376.

Research output: Chapter in Book/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Network traffic exploration on a many-core computing platform

T2 - 11th Conference on Ph.D. Research in Microelectronics and Electronics, PRIME 2015

AU - Liu, Gengting

AU - Camilleri, Patrick

AU - Furber, Stephen

AU - Garside, James

PY - 2015/9/9

Y1 - 2015/9/9

N2 - The performance of modern supercomputers is ever-increasing. Different kinds of massively parallel programs are written to maximally utilise the computing power provided by these many-core computing machines. However, this performance shrinks when network congestion occurs. SpiNNaker is an energy-efficient and highly parallel computing platform, which has built-in diagnostic hardware and congestion-aware adaptive routing. This paper describes the diagnostic technology available in SpiNNaker machines and presents a new software tool called SpiNNaker real-time traffic visualiser which adopts visualisation technology to explore the network traffic in SpiNNaker machines. This visualiser can assist application developers in detecting network traffic congestion with the provision of real-time configuration and data-logging functions.

AB - The performance of modern supercomputers is ever-increasing. Different kinds of massively parallel programs are written to maximally utilise the computing power provided by these many-core computing machines. However, this performance shrinks when network congestion occurs. SpiNNaker is an energy-efficient and highly parallel computing platform, which has built-in diagnostic hardware and congestion-aware adaptive routing. This paper describes the diagnostic technology available in SpiNNaker machines and presents a new software tool called SpiNNaker real-time traffic visualiser which adopts visualisation technology to explore the network traffic in SpiNNaker machines. This visualiser can assist application developers in detecting network traffic congestion with the provision of real-time configuration and data-logging functions.

KW - Chip Multiprocessor

KW - Network congestion

KW - Network on Chip

KW - Network traffic visualisation

KW - SpiNNaker project

UR - https://www.scopus.com/pages/publications/84946831000

U2 - 10.1109/PRIME.2015.7251376

DO - 10.1109/PRIME.2015.7251376

M3 - Conference contribution

AN - SCOPUS:84946831000

SN - 9781479982295

SP - 228

EP - 231

BT - 2015 11th Conference on Ph.D. Research in Microelectronics and Electronics, PRIME 2015

PB - IEEE

Y2 - 29 June 2015 through 2 July 2015

ER -

Network traffic exploration on a many-core computing platform: SpiNNaker real-time traffic visualiser

Abstract

Conference

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this