Using a master and slave approach for GPGPU computing to achieve optimal scaling in a 3D real-time simulation

Gregory Gutmann; Daisuke Inoue; Akira Kakugo; Akihiko Konagaya

doi:10.1109/NEMS.2016.7758208

Using a master and slave approach for GPGPU computing to achieve optimal scaling in a 3D real-time simulation

Gregory Gutmann, Daisuke Inoue, Akira Kakugo, Akihiko Konagaya

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

2 Citations (Scopus)

Abstract

With the ever increasing computational demand of scientific research and data analysis, there has been a migration towards GPU computing. GPU are now the primary source of compute power in most top supercomputers. But in order to make use of the power programs must utilize more than a single GPU. Within this paper we will explain various approaches we have taken to utilize multiple GPU, and attempt to reach close to perfect scaling on a multi-step simulation. The result of this is having developed our simulation to be computed on a master and slave setup of GPU. Our simulation mentioned is being developed for the purpose of simulating microtubule dynamics on a gliding assay.

Original language	English
Title of host publication	2016 IEEE 11th Annual International Conference on Nano/Micro Engineered and Molecular Systems, NEMS 2016
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	95-100
Number of pages	6
ISBN (Electronic)	9781509019472
DOIs	https://doi.org/10.1109/NEMS.2016.7758208
Publication status	Published - Nov 28 2016
Externally published	Yes
Event	11th IEEE Annual International Conference on Nano/Micro Engineered and Molecular Systems, NEMS 2016 - Sendai, Japan Duration: Apr 17 2016 → Apr 20 2016

Publication series

Name	2016 IEEE 11th Annual International Conference on Nano/Micro Engineered and Molecular Systems, NEMS 2016

Other

Other	11th IEEE Annual International Conference on Nano/Micro Engineered and Molecular Systems, NEMS 2016
Country/Territory	Japan
City	Sendai
Period	4/17/16 → 4/20/16

All Science Journal Classification (ASJC) codes

Industrial and Manufacturing Engineering
Mechanical Engineering
Mechanics of Materials
Electronic, Optical and Magnetic Materials

Access to Document

10.1109/NEMS.2016.7758208

Cite this

Gutmann, G., Inoue, D., Kakugo, A., & Konagaya, A. (2016). Using a master and slave approach for GPGPU computing to achieve optimal scaling in a 3D real-time simulation. In 2016 IEEE 11th Annual International Conference on Nano/Micro Engineered and Molecular Systems, NEMS 2016 (pp. 95-100). Article 7758208 (2016 IEEE 11th Annual International Conference on Nano/Micro Engineered and Molecular Systems, NEMS 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/NEMS.2016.7758208

Using a master and slave approach for GPGPU computing to achieve optimal scaling in a 3D real-time simulation. / Gutmann, Gregory; Inoue, Daisuke; Kakugo, Akira et al.
2016 IEEE 11th Annual International Conference on Nano/Micro Engineered and Molecular Systems, NEMS 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 95-100 7758208 (2016 IEEE 11th Annual International Conference on Nano/Micro Engineered and Molecular Systems, NEMS 2016).

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

Gutmann, G, Inoue, D, Kakugo, A & Konagaya, A 2016, Using a master and slave approach for GPGPU computing to achieve optimal scaling in a 3D real-time simulation. in 2016 IEEE 11th Annual International Conference on Nano/Micro Engineered and Molecular Systems, NEMS 2016., 7758208, 2016 IEEE 11th Annual International Conference on Nano/Micro Engineered and Molecular Systems, NEMS 2016, Institute of Electrical and Electronics Engineers Inc., pp. 95-100, 11th IEEE Annual International Conference on Nano/Micro Engineered and Molecular Systems, NEMS 2016, Sendai, Japan, 4/17/16. https://doi.org/10.1109/NEMS.2016.7758208

Gutmann G, Inoue D, Kakugo A, Konagaya A. Using a master and slave approach for GPGPU computing to achieve optimal scaling in a 3D real-time simulation. In 2016 IEEE 11th Annual International Conference on Nano/Micro Engineered and Molecular Systems, NEMS 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 95-100. 7758208. (2016 IEEE 11th Annual International Conference on Nano/Micro Engineered and Molecular Systems, NEMS 2016). doi: 10.1109/NEMS.2016.7758208

Gutmann, Gregory ; Inoue, Daisuke ; Kakugo, Akira et al. / Using a master and slave approach for GPGPU computing to achieve optimal scaling in a 3D real-time simulation. 2016 IEEE 11th Annual International Conference on Nano/Micro Engineered and Molecular Systems, NEMS 2016. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 95-100 (2016 IEEE 11th Annual International Conference on Nano/Micro Engineered and Molecular Systems, NEMS 2016).

@inproceedings{c896b942ac8443a68778c95054563f88,

title = "Using a master and slave approach for GPGPU computing to achieve optimal scaling in a 3D real-time simulation",

abstract = "With the ever increasing computational demand of scientific research and data analysis, there has been a migration towards GPU computing. GPU are now the primary source of compute power in most top supercomputers. But in order to make use of the power programs must utilize more than a single GPU. Within this paper we will explain various approaches we have taken to utilize multiple GPU, and attempt to reach close to perfect scaling on a multi-step simulation. The result of this is having developed our simulation to be computed on a master and slave setup of GPU. Our simulation mentioned is being developed for the purpose of simulating microtubule dynamics on a gliding assay.",

author = "Gregory Gutmann and Daisuke Inoue and Akira Kakugo and Akihiko Konagaya",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 11th IEEE Annual International Conference on Nano/Micro Engineered and Molecular Systems, NEMS 2016 ; Conference date: 17-04-2016 Through 20-04-2016",

year = "2016",

month = nov,

day = "28",

doi = "10.1109/NEMS.2016.7758208",

language = "English",

series = "2016 IEEE 11th Annual International Conference on Nano/Micro Engineered and Molecular Systems, NEMS 2016",

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

pages = "95--100",

booktitle = "2016 IEEE 11th Annual International Conference on Nano/Micro Engineered and Molecular Systems, NEMS 2016",

address = "United States",

}

TY - GEN

T1 - Using a master and slave approach for GPGPU computing to achieve optimal scaling in a 3D real-time simulation

AU - Gutmann, Gregory

AU - Inoue, Daisuke

AU - Kakugo, Akira

AU - Konagaya, Akihiko

PY - 2016/11/28

Y1 - 2016/11/28

N2 - With the ever increasing computational demand of scientific research and data analysis, there has been a migration towards GPU computing. GPU are now the primary source of compute power in most top supercomputers. But in order to make use of the power programs must utilize more than a single GPU. Within this paper we will explain various approaches we have taken to utilize multiple GPU, and attempt to reach close to perfect scaling on a multi-step simulation. The result of this is having developed our simulation to be computed on a master and slave setup of GPU. Our simulation mentioned is being developed for the purpose of simulating microtubule dynamics on a gliding assay.

AB - With the ever increasing computational demand of scientific research and data analysis, there has been a migration towards GPU computing. GPU are now the primary source of compute power in most top supercomputers. But in order to make use of the power programs must utilize more than a single GPU. Within this paper we will explain various approaches we have taken to utilize multiple GPU, and attempt to reach close to perfect scaling on a multi-step simulation. The result of this is having developed our simulation to be computed on a master and slave setup of GPU. Our simulation mentioned is being developed for the purpose of simulating microtubule dynamics on a gliding assay.

UR - http://www.scopus.com/inward/record.url?scp=85007190429&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85007190429&partnerID=8YFLogxK

U2 - 10.1109/NEMS.2016.7758208

DO - 10.1109/NEMS.2016.7758208

M3 - Conference contribution

AN - SCOPUS:85007190429

T3 - 2016 IEEE 11th Annual International Conference on Nano/Micro Engineered and Molecular Systems, NEMS 2016

SP - 95

EP - 100

BT - 2016 IEEE 11th Annual International Conference on Nano/Micro Engineered and Molecular Systems, NEMS 2016

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 11th IEEE Annual International Conference on Nano/Micro Engineered and Molecular Systems, NEMS 2016

Y2 - 17 April 2016 through 20 April 2016

ER -

Using a master and slave approach for GPGPU computing to achieve optimal scaling in a 3D real-time simulation

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this