Multi-Chip Dataflow Architecture for Massive Scale Biophysically Accurate Neuron Simulation

J. Hofmann; A. Zjajo; C. Galuzzi; R. van Leuken

doi:10.1109/EMBC.2016.7592053

Multi-Chip Dataflow Architecture for Massive Scale Biophysically Accurate Neuron Simulation

J. Hofmann^*, A. Zjajo, C. Galuzzi, R. van Leuken

^*Corresponding author for this work

Advanced Computing Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

Abstract

State-of-the-art neuron simulators are capable of simulating at most few tens/hundreds of neurons in real-time due to the exponential growth in the communication costs with the number of simulated neurons. In this paper, we present a novel, reconfigurable, multi-chip system architecture based on localized communication, which effectively reduces the communication cost to a linear growth. The system is very flexible and it allows to tune, at run-time, various parameters, e.g. the intracellular concentration of chemical compounds, the interconnection scheme between the neurons. Experimental results indicate that the proposed system architecture allows the simulation of up to few thousands biophysically accurate neurons over multiple chips.

Original language	English
Title of host publication	2016 38TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC)
Publisher	IEEE
Pages	5829-5832
Number of pages	4
DOIs	https://doi.org/10.1109/EMBC.2016.7592053
Publication status	Published - Aug 2016
Event	38th Annual International Conference of the IEEE-Engineering in Medicine and Biology Society (EMBC) - Orlando, United States Duration: 16 Aug 2016 → 20 Aug 2016 https://embc.embs.org/2016/#:~:text=August%2016%2D20%2C%202016,USA%20on%20August%2016%2D20.

Publication series

Series	IEEE Engineering in Medicine and Biology Society Conference Proceedings
ISSN	1557-170X

Conference

Conference	38th Annual International Conference of the IEEE-Engineering in Medicine and Biology Society (EMBC)
Abbreviated title	Empowering Individuals Healthcare Decisions through Technology
Country/Territory	United States
City	Orlando
Period	16/08/16 → 20/08/16
Internet address	https://embc.embs.org/2016/#:~:text=August%2016%2D20%2C%202016,USA%20on%20August%2016%2D20.

Access to Document

10.1109/EMBC.2016.7592053

Cite this

@inproceedings{ff0968b74f6e41a882db5d75ac128059,

title = "Multi-Chip Dataflow Architecture for Massive Scale Biophysically Accurate Neuron Simulation",

abstract = "State-of-the-art neuron simulators are capable of simulating at most few tens/hundreds of neurons in real-time due to the exponential growth in the communication costs with the number of simulated neurons. In this paper, we present a novel, reconfigurable, multi-chip system architecture based on localized communication, which effectively reduces the communication cost to a linear growth. The system is very flexible and it allows to tune, at run-time, various parameters, e.g. the intracellular concentration of chemical compounds, the interconnection scheme between the neurons. Experimental results indicate that the proposed system architecture allows the simulation of up to few thousands biophysically accurate neurons over multiple chips.",

author = "J. Hofmann and A. Zjajo and C. Galuzzi and {van Leuken}, R.",

year = "2016",

month = aug,

doi = "10.1109/EMBC.2016.7592053",

language = "English",

series = "IEEE Engineering in Medicine and Biology Society Conference Proceedings",

publisher = "IEEE",

pages = "5829--5832",

booktitle = "2016 38TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC)",

address = "United States",

note = "38th Annual International Conference of the IEEE-Engineering in Medicine and Biology Society (EMBC), Empowering Individuals Healthcare Decisions through Technology ; Conference date: 16-08-2016 Through 20-08-2016",

url = "https://embc.embs.org/2016/#:~:text=August%2016%2D20%2C%202016,USA%20on%20August%2016%2D20.",

}

Hofmann, J, Zjajo, A, Galuzzi, C & van Leuken, R 2016, Multi-Chip Dataflow Architecture for Massive Scale Biophysically Accurate Neuron Simulation. in 2016 38TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC). IEEE, IEEE Engineering in Medicine and Biology Society Conference Proceedings, pp. 5829-5832, 38th Annual International Conference of the IEEE-Engineering in Medicine and Biology Society (EMBC), Orlando, Florida, United States, 16/08/16. https://doi.org/10.1109/EMBC.2016.7592053

Multi-Chip Dataflow Architecture for Massive Scale Biophysically Accurate Neuron Simulation. / Hofmann, J.; Zjajo, A.; Galuzzi, C. et al.
2016 38TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC). IEEE, 2016. p. 5829-5832 (IEEE Engineering in Medicine and Biology Society Conference Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

TY - GEN

T1 - Multi-Chip Dataflow Architecture for Massive Scale Biophysically Accurate Neuron Simulation

AU - Hofmann, J.

AU - Zjajo, A.

AU - Galuzzi, C.

AU - van Leuken, R.

PY - 2016/8

Y1 - 2016/8

N2 - State-of-the-art neuron simulators are capable of simulating at most few tens/hundreds of neurons in real-time due to the exponential growth in the communication costs with the number of simulated neurons. In this paper, we present a novel, reconfigurable, multi-chip system architecture based on localized communication, which effectively reduces the communication cost to a linear growth. The system is very flexible and it allows to tune, at run-time, various parameters, e.g. the intracellular concentration of chemical compounds, the interconnection scheme between the neurons. Experimental results indicate that the proposed system architecture allows the simulation of up to few thousands biophysically accurate neurons over multiple chips.

AB - State-of-the-art neuron simulators are capable of simulating at most few tens/hundreds of neurons in real-time due to the exponential growth in the communication costs with the number of simulated neurons. In this paper, we present a novel, reconfigurable, multi-chip system architecture based on localized communication, which effectively reduces the communication cost to a linear growth. The system is very flexible and it allows to tune, at run-time, various parameters, e.g. the intracellular concentration of chemical compounds, the interconnection scheme between the neurons. Experimental results indicate that the proposed system architecture allows the simulation of up to few thousands biophysically accurate neurons over multiple chips.

U2 - 10.1109/EMBC.2016.7592053

DO - 10.1109/EMBC.2016.7592053

M3 - Conference article in proceeding

T3 - IEEE Engineering in Medicine and Biology Society Conference Proceedings

SP - 5829

EP - 5832

BT - 2016 38TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC)

PB - IEEE

T2 - 38th Annual International Conference of the IEEE-Engineering in Medicine and Biology Society (EMBC)

Y2 - 16 August 2016 through 20 August 2016

ER -

Hofmann J, Zjajo A, Galuzzi C, van Leuken R. Multi-Chip Dataflow Architecture for Massive Scale Biophysically Accurate Neuron Simulation. In 2016 38TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC). IEEE. 2016. p. 5829-5832. (IEEE Engineering in Medicine and Biology Society Conference Proceedings). doi: 10.1109/EMBC.2016.7592053