A Case for Remote GPUs over 10GbE Network for VR Applications

Shin Morishima, Masahiro Okazaki, Hiroki Matsutani

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

VR technology that enables users to experience environments made by computer similar to real environments has become popular. In VR technology, computation cost of graphic processing is high and thus it requires a high-end GPU because high-quality pictures that look like real environments are processed while reflecting sensor information. Therefore, users have to prepare a computer with a high-end GPU, which requires a high cost. In this paper, we propose to connect GPU cluster and user-side computers via 10GbE (10Gbit Ethernet) network so that graphic processing for HMDs is done by the GPU cluster via a network. In this way, users can use HMD with inexpensive computers because they do not have to prepare computers with high-end GPUs. In this paper, we propose an index to evaluate performance of VR processing tasks in remote GPU environment and evaluate the performance in the remote GPU environment based on this index. We also propose a condition that does not degrade user experience in the remote GPU environment and allocation methods of multiple tasks to GPUs under this condition. The evaluation results of the proposed allocation methods show that if there is a high-load task, the method that preferentially allocates tasks to GPUs with low bandwidth achieves high performance; otherwise the method that preferentially allocates tasks to GPUs with high utilization achieves a high performance.

Original languageEnglish
Title of host publicationProceedings of the 8th International Symposium on Highly-Efficient Accelerators and Reconfigurable Technologies, HEART 2017
PublisherAssociation for Computing Machinery
ISBN (Electronic)9781450353168
DOIs
Publication statusPublished - 2017 Jun 7
Event8th International Symposium on Highly-Efficient Accelerators and Reconfigurable Technologies, HEART 2017 - Bochum, Germany
Duration: 2017 Jun 72017 Jun 9

Other

Other8th International Symposium on Highly-Efficient Accelerators and Reconfigurable Technologies, HEART 2017
CountryGermany
CityBochum
Period17/6/717/6/9

Fingerprint

Ethernet
Helmet mounted displays
Graphics processing unit
Processing
Costs
Bandwidth

Keywords

  • 10Gbit Ethernet
  • GPU
  • Virtual Reality

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Software

Cite this

Morishima, S., Okazaki, M., & Matsutani, H. (2017). A Case for Remote GPUs over 10GbE Network for VR Applications. In Proceedings of the 8th International Symposium on Highly-Efficient Accelerators and Reconfigurable Technologies, HEART 2017 [19] Association for Computing Machinery. https://doi.org/10.1145/3120895.3120914

A Case for Remote GPUs over 10GbE Network for VR Applications. / Morishima, Shin; Okazaki, Masahiro; Matsutani, Hiroki.

Proceedings of the 8th International Symposium on Highly-Efficient Accelerators and Reconfigurable Technologies, HEART 2017. Association for Computing Machinery, 2017. 19.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Morishima, S, Okazaki, M & Matsutani, H 2017, A Case for Remote GPUs over 10GbE Network for VR Applications. in Proceedings of the 8th International Symposium on Highly-Efficient Accelerators and Reconfigurable Technologies, HEART 2017., 19, Association for Computing Machinery, 8th International Symposium on Highly-Efficient Accelerators and Reconfigurable Technologies, HEART 2017, Bochum, Germany, 17/6/7. https://doi.org/10.1145/3120895.3120914
Morishima S, Okazaki M, Matsutani H. A Case for Remote GPUs over 10GbE Network for VR Applications. In Proceedings of the 8th International Symposium on Highly-Efficient Accelerators and Reconfigurable Technologies, HEART 2017. Association for Computing Machinery. 2017. 19 https://doi.org/10.1145/3120895.3120914
Morishima, Shin ; Okazaki, Masahiro ; Matsutani, Hiroki. / A Case for Remote GPUs over 10GbE Network for VR Applications. Proceedings of the 8th International Symposium on Highly-Efficient Accelerators and Reconfigurable Technologies, HEART 2017. Association for Computing Machinery, 2017.
@inproceedings{36b24ad9bfa14abd92d70bc695ba09d5,
title = "A Case for Remote GPUs over 10GbE Network for VR Applications",
abstract = "VR technology that enables users to experience environments made by computer similar to real environments has become popular. In VR technology, computation cost of graphic processing is high and thus it requires a high-end GPU because high-quality pictures that look like real environments are processed while reflecting sensor information. Therefore, users have to prepare a computer with a high-end GPU, which requires a high cost. In this paper, we propose to connect GPU cluster and user-side computers via 10GbE (10Gbit Ethernet) network so that graphic processing for HMDs is done by the GPU cluster via a network. In this way, users can use HMD with inexpensive computers because they do not have to prepare computers with high-end GPUs. In this paper, we propose an index to evaluate performance of VR processing tasks in remote GPU environment and evaluate the performance in the remote GPU environment based on this index. We also propose a condition that does not degrade user experience in the remote GPU environment and allocation methods of multiple tasks to GPUs under this condition. The evaluation results of the proposed allocation methods show that if there is a high-load task, the method that preferentially allocates tasks to GPUs with low bandwidth achieves high performance; otherwise the method that preferentially allocates tasks to GPUs with high utilization achieves a high performance.",
keywords = "10Gbit Ethernet, GPU, Virtual Reality",
author = "Shin Morishima and Masahiro Okazaki and Hiroki Matsutani",
year = "2017",
month = "6",
day = "7",
doi = "10.1145/3120895.3120914",
language = "English",
booktitle = "Proceedings of the 8th International Symposium on Highly-Efficient Accelerators and Reconfigurable Technologies, HEART 2017",
publisher = "Association for Computing Machinery",

}

TY - GEN

T1 - A Case for Remote GPUs over 10GbE Network for VR Applications

AU - Morishima, Shin

AU - Okazaki, Masahiro

AU - Matsutani, Hiroki

PY - 2017/6/7

Y1 - 2017/6/7

N2 - VR technology that enables users to experience environments made by computer similar to real environments has become popular. In VR technology, computation cost of graphic processing is high and thus it requires a high-end GPU because high-quality pictures that look like real environments are processed while reflecting sensor information. Therefore, users have to prepare a computer with a high-end GPU, which requires a high cost. In this paper, we propose to connect GPU cluster and user-side computers via 10GbE (10Gbit Ethernet) network so that graphic processing for HMDs is done by the GPU cluster via a network. In this way, users can use HMD with inexpensive computers because they do not have to prepare computers with high-end GPUs. In this paper, we propose an index to evaluate performance of VR processing tasks in remote GPU environment and evaluate the performance in the remote GPU environment based on this index. We also propose a condition that does not degrade user experience in the remote GPU environment and allocation methods of multiple tasks to GPUs under this condition. The evaluation results of the proposed allocation methods show that if there is a high-load task, the method that preferentially allocates tasks to GPUs with low bandwidth achieves high performance; otherwise the method that preferentially allocates tasks to GPUs with high utilization achieves a high performance.

AB - VR technology that enables users to experience environments made by computer similar to real environments has become popular. In VR technology, computation cost of graphic processing is high and thus it requires a high-end GPU because high-quality pictures that look like real environments are processed while reflecting sensor information. Therefore, users have to prepare a computer with a high-end GPU, which requires a high cost. In this paper, we propose to connect GPU cluster and user-side computers via 10GbE (10Gbit Ethernet) network so that graphic processing for HMDs is done by the GPU cluster via a network. In this way, users can use HMD with inexpensive computers because they do not have to prepare computers with high-end GPUs. In this paper, we propose an index to evaluate performance of VR processing tasks in remote GPU environment and evaluate the performance in the remote GPU environment based on this index. We also propose a condition that does not degrade user experience in the remote GPU environment and allocation methods of multiple tasks to GPUs under this condition. The evaluation results of the proposed allocation methods show that if there is a high-load task, the method that preferentially allocates tasks to GPUs with low bandwidth achieves high performance; otherwise the method that preferentially allocates tasks to GPUs with high utilization achieves a high performance.

KW - 10Gbit Ethernet

KW - GPU

KW - Virtual Reality

UR - http://www.scopus.com/inward/record.url?scp=85040703275&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85040703275&partnerID=8YFLogxK

U2 - 10.1145/3120895.3120914

DO - 10.1145/3120895.3120914

M3 - Conference contribution

BT - Proceedings of the 8th International Symposium on Highly-Efficient Accelerators and Reconfigurable Technologies, HEART 2017

PB - Association for Computing Machinery

ER -