Optimal mapping of inferior olive neuron simulations on the Single-Chip Cloud Computer

Dimitrios Rodopoulos; Giorgos Chatzikonstantis; Andreas Pantelopoulos; Dimitrios Soudris; Chris I. De Zeeuw; Christos Strydis

doi:10.1109/SAMOS.2014.6893235

Optimal mapping of inferior olive neuron simulations on the Single-Chip Cloud Computer

Dimitrios Rodopoulos^*, Giorgos Chatzikonstantis, Andreas Pantelopoulos, Dimitrios Soudris, Chris I. De Zeeuw, Christos Strydis

^*Corresponding author for this work

Neurosciences

Research output: Chapter/Conference proceeding › Conference proceeding › Academic › peer-review

3 Citations (Scopus)

Abstract

Biologically accurate neuron simulations are increasingly important in research related to brain activity. They are computationally intensive and feature data and task parallelism. In this paper, we present a case study for the mapping of a biologically accurate inferior-olive (InfOli), neural cell simulator on an many-core research platform. The Single-Chip Cloud Computer (SCC) is an experimental processor created by Intel Labs. The target neurons provide a major input to the cerebellum and are involved in motor skills and space perception. We exploit task-and data-partitioning, scaling the simulation over more than 40,000 neurons. The voltage-and frequency-scaling capabilities of the chip are explored, achieving more than 20% energy savings with negligible performance degradation. Four platform configurations are evaluated and a mapping with balanced workload and constant voltage and frequency is formally derived as optimal.

Original language	English
Title of host publication	Proceedings - International Conference on Embedded Computer Systems
Subtitle of host publication	Architectures, Modeling and Simulation, SAMOS 2014
Editors	Alexander V. Veidenbaum, Carlo Galuzzi
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	367-374
Number of pages	8
ISBN (Electronic)	9781479937707
DOIs	https://doi.org/10.1109/SAMOS.2014.6893235
Publication status	Published - 2014
Event	14th International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation, SAMOS 2014 - Samos, Greece Duration: 14 Jul 2014 → 17 Jul 2014

Publication series

Series	Proceedings - International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation, SAMOS 2014

Conference

Conference	14th International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation, SAMOS 2014
Country/Territory	Greece
City	Samos
Period	14/07/14 → 17/07/14

Bibliographical note

Publisher Copyright:
© 2014 IEEE.

Access to Document

10.1109/SAMOS.2014.6893235

Cite this

Rodopoulos, D., Chatzikonstantis, G., Pantelopoulos, A., Soudris, D., De Zeeuw, C. I., & Strydis, C. (2014). Optimal mapping of inferior olive neuron simulations on the Single-Chip Cloud Computer. In A. V. Veidenbaum, & C. Galuzzi (Eds.), Proceedings - International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation, SAMOS 2014 (pp. 367-374). [6893235] Institute of Electrical and Electronics Engineers Inc.. Proceedings - International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation, SAMOS 2014 https://doi.org/10.1109/SAMOS.2014.6893235

Rodopoulos, Dimitrios ; Chatzikonstantis, Giorgos ; Pantelopoulos, Andreas et al. / Optimal mapping of inferior olive neuron simulations on the Single-Chip Cloud Computer. Proceedings - International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation, SAMOS 2014. editor / Alexander V. Veidenbaum ; Carlo Galuzzi. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 367-374 (Proceedings - International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation, SAMOS 2014).

@inproceedings{9ffce4df7dc74bfbbc0d3b7ffdb7680c,

title = "Optimal mapping of inferior olive neuron simulations on the Single-Chip Cloud Computer",

abstract = "Biologically accurate neuron simulations are increasingly important in research related to brain activity. They are computationally intensive and feature data and task parallelism. In this paper, we present a case study for the mapping of a biologically accurate inferior-olive (InfOli), neural cell simulator on an many-core research platform. The Single-Chip Cloud Computer (SCC) is an experimental processor created by Intel Labs. The target neurons provide a major input to the cerebellum and are involved in motor skills and space perception. We exploit task-and data-partitioning, scaling the simulation over more than 40,000 neurons. The voltage-and frequency-scaling capabilities of the chip are explored, achieving more than 20% energy savings with negligible performance degradation. Four platform configurations are evaluated and a mapping with balanced workload and constant voltage and frequency is formally derived as optimal.",

author = "Dimitrios Rodopoulos and Giorgos Chatzikonstantis and Andreas Pantelopoulos and Dimitrios Soudris and {De Zeeuw}, {Chris I.} and Christos Strydis",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 14th International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation, SAMOS 2014 ; Conference date: 14-07-2014 Through 17-07-2014",

year = "2014",

doi = "10.1109/SAMOS.2014.6893235",

language = "English",

series = "Proceedings - International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation, SAMOS 2014",

pages = "367--374",

editor = "Veidenbaum, {Alexander V.} and Carlo Galuzzi",

booktitle = "Proceedings - International Conference on Embedded Computer Systems",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

}

Rodopoulos, D, Chatzikonstantis, G, Pantelopoulos, A, Soudris, D, De Zeeuw, CI & Strydis, C 2014, Optimal mapping of inferior olive neuron simulations on the Single-Chip Cloud Computer. in AV Veidenbaum & C Galuzzi (eds), Proceedings - International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation, SAMOS 2014., 6893235, Institute of Electrical and Electronics Engineers Inc., Proceedings - International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation, SAMOS 2014, pp. 367-374, 14th International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation, SAMOS 2014, Samos, Greece, 14/07/14. https://doi.org/10.1109/SAMOS.2014.6893235

Optimal mapping of inferior olive neuron simulations on the Single-Chip Cloud Computer. / Rodopoulos, Dimitrios; Chatzikonstantis, Giorgos; Pantelopoulos, Andreas et al.
Proceedings - International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation, SAMOS 2014. ed. / Alexander V. Veidenbaum; Carlo Galuzzi. Institute of Electrical and Electronics Engineers Inc., 2014. p. 367-374 6893235 (Proceedings - International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation, SAMOS 2014).

Research output: Chapter/Conference proceeding › Conference proceeding › Academic › peer-review

TY - GEN

T1 - Optimal mapping of inferior olive neuron simulations on the Single-Chip Cloud Computer

AU - Rodopoulos, Dimitrios

AU - Chatzikonstantis, Giorgos

AU - Pantelopoulos, Andreas

AU - Soudris, Dimitrios

AU - De Zeeuw, Chris I.

AU - Strydis, Christos

PY - 2014

Y1 - 2014

N2 - Biologically accurate neuron simulations are increasingly important in research related to brain activity. They are computationally intensive and feature data and task parallelism. In this paper, we present a case study for the mapping of a biologically accurate inferior-olive (InfOli), neural cell simulator on an many-core research platform. The Single-Chip Cloud Computer (SCC) is an experimental processor created by Intel Labs. The target neurons provide a major input to the cerebellum and are involved in motor skills and space perception. We exploit task-and data-partitioning, scaling the simulation over more than 40,000 neurons. The voltage-and frequency-scaling capabilities of the chip are explored, achieving more than 20% energy savings with negligible performance degradation. Four platform configurations are evaluated and a mapping with balanced workload and constant voltage and frequency is formally derived as optimal.

AB - Biologically accurate neuron simulations are increasingly important in research related to brain activity. They are computationally intensive and feature data and task parallelism. In this paper, we present a case study for the mapping of a biologically accurate inferior-olive (InfOli), neural cell simulator on an many-core research platform. The Single-Chip Cloud Computer (SCC) is an experimental processor created by Intel Labs. The target neurons provide a major input to the cerebellum and are involved in motor skills and space perception. We exploit task-and data-partitioning, scaling the simulation over more than 40,000 neurons. The voltage-and frequency-scaling capabilities of the chip are explored, achieving more than 20% energy savings with negligible performance degradation. Four platform configurations are evaluated and a mapping with balanced workload and constant voltage and frequency is formally derived as optimal.

UR - http://www.scopus.com/inward/record.url?scp=84907900150&partnerID=8YFLogxK

U2 - 10.1109/SAMOS.2014.6893235

DO - 10.1109/SAMOS.2014.6893235

M3 - Conference proceeding

AN - SCOPUS:84907900150

T3 - Proceedings - International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation, SAMOS 2014

SP - 367

EP - 374

BT - Proceedings - International Conference on Embedded Computer Systems

A2 - Veidenbaum, Alexander V.

A2 - Galuzzi, Carlo

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 14th International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation, SAMOS 2014

Y2 - 14 July 2014 through 17 July 2014

ER -

Rodopoulos D, Chatzikonstantis G, Pantelopoulos A, Soudris D, De Zeeuw CI , Strydis C. Optimal mapping of inferior olive neuron simulations on the Single-Chip Cloud Computer. In Veidenbaum AV, Galuzzi C, editors, Proceedings - International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation, SAMOS 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 367-374. 6893235. (Proceedings - International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation, SAMOS 2014). doi: 10.1109/SAMOS.2014.6893235

Optimal mapping of inferior olive neuron simulations on the Single-Chip Cloud Computer

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this