Parallelizing Hilbert-Huang transform on a GPU

Pulung Waskito, Shinobu Miwa, Yasue Mitsukura, Hironori Nakajo

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

9 Citations (Scopus)

Abstract

In this paper, we show parallel implementation of Hilbert-Huang Transform on GPU. This implementation focused on the reducing the computation complexity from O(N) on a single CPU to O(N/P log (N)) on GPU, as well as the use of 'shared-global' switching method to increase performance. Evaluation results show our single GPU implementation using Tesla C1060 achieves 29.0x speedup in best case, and a total of 7.1x speedup for all results when compared to a single Intel dual core CPU.

Original languageEnglish
Title of host publicationProceedings - 2010 1st International Conference on Networking and Computing, ICNC 2010
Pages184-190
Number of pages7
DOIs
Publication statusPublished - 2010
Externally publishedYes
Event1st International Conference on Networking and Computing, ICNC 2010 - Higashi-Hiroshima, Japan
Duration: 2010 Nov 172010 Nov 19

Other

Other1st International Conference on Networking and Computing, ICNC 2010
CountryJapan
CityHigashi-Hiroshima
Period10/11/1710/11/19

Fingerprint

Program processors
Mathematical transformations
Graphics processing unit

Keywords

  • CUDA
  • Empirical mode decomposition (EMD)
  • GPU
  • Hilbert-Huang transform (HHT)

ASJC Scopus subject areas

  • Computer Networks and Communications

Cite this

Waskito, P., Miwa, S., Mitsukura, Y., & Nakajo, H. (2010). Parallelizing Hilbert-Huang transform on a GPU. In Proceedings - 2010 1st International Conference on Networking and Computing, ICNC 2010 (pp. 184-190). [5695232] https://doi.org/10.1109/IC-NC.2010.44

Parallelizing Hilbert-Huang transform on a GPU. / Waskito, Pulung; Miwa, Shinobu; Mitsukura, Yasue; Nakajo, Hironori.

Proceedings - 2010 1st International Conference on Networking and Computing, ICNC 2010. 2010. p. 184-190 5695232.

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

Waskito, P, Miwa, S, Mitsukura, Y & Nakajo, H 2010, Parallelizing Hilbert-Huang transform on a GPU. in Proceedings - 2010 1st International Conference on Networking and Computing, ICNC 2010., 5695232, pp. 184-190, 1st International Conference on Networking and Computing, ICNC 2010, Higashi-Hiroshima, Japan, 10/11/17. https://doi.org/10.1109/IC-NC.2010.44
Waskito P, Miwa S, Mitsukura Y, Nakajo H. Parallelizing Hilbert-Huang transform on a GPU. In Proceedings - 2010 1st International Conference on Networking and Computing, ICNC 2010. 2010. p. 184-190. 5695232 https://doi.org/10.1109/IC-NC.2010.44
Waskito, Pulung ; Miwa, Shinobu ; Mitsukura, Yasue ; Nakajo, Hironori. / Parallelizing Hilbert-Huang transform on a GPU. Proceedings - 2010 1st International Conference on Networking and Computing, ICNC 2010. 2010. pp. 184-190
@inproceedings{5418bc44e38741658fd1b5bf70344846,
title = "Parallelizing Hilbert-Huang transform on a GPU",
abstract = "In this paper, we show parallel implementation of Hilbert-Huang Transform on GPU. This implementation focused on the reducing the computation complexity from O(N) on a single CPU to O(N/P log (N)) on GPU, as well as the use of 'shared-global' switching method to increase performance. Evaluation results show our single GPU implementation using Tesla C1060 achieves 29.0x speedup in best case, and a total of 7.1x speedup for all results when compared to a single Intel dual core CPU.",
keywords = "CUDA, Empirical mode decomposition (EMD), GPU, Hilbert-Huang transform (HHT)",
author = "Pulung Waskito and Shinobu Miwa and Yasue Mitsukura and Hironori Nakajo",
year = "2010",
doi = "10.1109/IC-NC.2010.44",
language = "English",
isbn = "9780769542775",
pages = "184--190",
booktitle = "Proceedings - 2010 1st International Conference on Networking and Computing, ICNC 2010",

}

TY - GEN

T1 - Parallelizing Hilbert-Huang transform on a GPU

AU - Waskito, Pulung

AU - Miwa, Shinobu

AU - Mitsukura, Yasue

AU - Nakajo, Hironori

PY - 2010

Y1 - 2010

N2 - In this paper, we show parallel implementation of Hilbert-Huang Transform on GPU. This implementation focused on the reducing the computation complexity from O(N) on a single CPU to O(N/P log (N)) on GPU, as well as the use of 'shared-global' switching method to increase performance. Evaluation results show our single GPU implementation using Tesla C1060 achieves 29.0x speedup in best case, and a total of 7.1x speedup for all results when compared to a single Intel dual core CPU.

AB - In this paper, we show parallel implementation of Hilbert-Huang Transform on GPU. This implementation focused on the reducing the computation complexity from O(N) on a single CPU to O(N/P log (N)) on GPU, as well as the use of 'shared-global' switching method to increase performance. Evaluation results show our single GPU implementation using Tesla C1060 achieves 29.0x speedup in best case, and a total of 7.1x speedup for all results when compared to a single Intel dual core CPU.

KW - CUDA

KW - Empirical mode decomposition (EMD)

KW - GPU

KW - Hilbert-Huang transform (HHT)

UR - http://www.scopus.com/inward/record.url?scp=79951784325&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79951784325&partnerID=8YFLogxK

U2 - 10.1109/IC-NC.2010.44

DO - 10.1109/IC-NC.2010.44

M3 - Conference contribution

AN - SCOPUS:79951784325

SN - 9780769542775

SP - 184

EP - 190

BT - Proceedings - 2010 1st International Conference on Networking and Computing, ICNC 2010

ER -