Parallel Matrix Sort Using MPI and CUDA

Priyanka Ojha; Pratibha Singh; Gopalakrishna N. Kini; B. Ashwath Rao; Shwetha Rai

doi:10.1007/978-981-16-1089-9_45

Parallel Matrix Sort Using MPI and CUDA

Priyanka Ojha, Pratibha Singh, Gopalakrishna N. Kini, B. Ashwath Rao, Shwetha Rai

Department of Computer Science and Engineering, Manipal Institute of Technology, Manipal

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

Abstract

Sorted data is essential. Apart from information presentation or manual retrieval of information, sorted data is beneficial even when using machines’ computational power. In many science and engineering fields, the sorting of extensive dataset is essential in matrix form. Matrix sort is an algorithm, which can sort a large amount of data in matrix form efficiently. In this paper, parallel algorithms are developed for the Matrix Sort algorithm (designed by S. Kavitha et al. Int J Comput Appl 143(9):1–6, 2016) [1]. This algorithm sorts the matrix rows and columns in parallel, subsequently applying the further procedure on resultant data. The implementations of parallel algorithms have been discussed by comparing the execution time results obtained in sequential and parallel form.

Original language	English
Title of host publication	Communication and Intelligent Systems - Proceedings of ICCIS 2020
Editors	Harish Sharma, Mukesh Kumar Gupta, G. S. Tomar, Wang Lipo
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	575-583
Number of pages	9
ISBN (Print)	9789811610882
DOIs	https://doi.org/10.1007/978-981-16-1089-9_45
Publication status	Published - 2021
Event	2nd International Conference on Communication and Intelligent Systems, ICCIS 2020 - Virtual, Online Duration: 26-12-2020 → 27-12-2020

Publication series

Name	Lecture Notes in Networks and Systems
Volume	204
ISSN (Print)	2367-3370
ISSN (Electronic)	2367-3389

Conference

Conference	2nd International Conference on Communication and Intelligent Systems, ICCIS 2020
City	Virtual, Online
Period	26-12-20 → 27-12-20

All Science Journal Classification (ASJC) codes

Control and Systems Engineering
Signal Processing
Computer Networks and Communications

Access to Document

10.1007/978-981-16-1089-9_45

Cite this

Ojha, P., Singh, P., Kini, G. N., Rao, B. A., & Rai, S. (2021). Parallel Matrix Sort Using MPI and CUDA. In H. Sharma, M. K. Gupta, G. S. Tomar, & W. Lipo (Eds.), Communication and Intelligent Systems - Proceedings of ICCIS 2020 (pp. 575-583). (Lecture Notes in Networks and Systems; Vol. 204). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-16-1089-9_45

@inproceedings{2408a288898b4f019320cdbe5e16ce5b,

title = "Parallel Matrix Sort Using MPI and CUDA",

abstract = "Sorted data is essential. Apart from information presentation or manual retrieval of information, sorted data is beneficial even when using machines{\textquoteright} computational power. In many science and engineering fields, the sorting of extensive dataset is essential in matrix form. Matrix sort is an algorithm, which can sort a large amount of data in matrix form efficiently. In this paper, parallel algorithms are developed for the Matrix Sort algorithm (designed by S. Kavitha et al. Int J Comput Appl 143(9):1–6, 2016) [1]. This algorithm sorts the matrix rows and columns in parallel, subsequently applying the further procedure on resultant data. The implementations of parallel algorithms have been discussed by comparing the execution time results obtained in sequential and parallel form.",

author = "Priyanka Ojha and Pratibha Singh and Kini, {Gopalakrishna N.} and Rao, {B. Ashwath} and Shwetha Rai",

note = "Publisher Copyright: {\textcopyright} 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.; 2nd International Conference on Communication and Intelligent Systems, ICCIS 2020 ; Conference date: 26-12-2020 Through 27-12-2020",

year = "2021",

doi = "10.1007/978-981-16-1089-9_45",

language = "English",

isbn = "9789811610882",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "575--583",

editor = "Harish Sharma and Gupta, {Mukesh Kumar} and Tomar, {G. S.} and Wang Lipo",

booktitle = "Communication and Intelligent Systems - Proceedings of ICCIS 2020",

address = "Germany",

}

Ojha, P, Singh, P, Kini, GN , Rao, BA & Rai, S 2021, Parallel Matrix Sort Using MPI and CUDA. in H Sharma, MK Gupta, GS Tomar & W Lipo (eds), Communication and Intelligent Systems - Proceedings of ICCIS 2020. Lecture Notes in Networks and Systems, vol. 204, Springer Science and Business Media Deutschland GmbH, pp. 575-583, 2nd International Conference on Communication and Intelligent Systems, ICCIS 2020, Virtual, Online, 26-12-20. https://doi.org/10.1007/978-981-16-1089-9_45

Parallel Matrix Sort Using MPI and CUDA. / Ojha, Priyanka; Singh, Pratibha; Kini, Gopalakrishna N. et al.
Communication and Intelligent Systems - Proceedings of ICCIS 2020. ed. / Harish Sharma; Mukesh Kumar Gupta; G. S. Tomar; Wang Lipo. Springer Science and Business Media Deutschland GmbH, 2021. p. 575-583 (Lecture Notes in Networks and Systems; Vol. 204).

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

TY - GEN

T1 - Parallel Matrix Sort Using MPI and CUDA

AU - Ojha, Priyanka

AU - Singh, Pratibha

AU - Kini, Gopalakrishna N.

AU - Rao, B. Ashwath

AU - Rai, Shwetha

PY - 2021

Y1 - 2021

N2 - Sorted data is essential. Apart from information presentation or manual retrieval of information, sorted data is beneficial even when using machines’ computational power. In many science and engineering fields, the sorting of extensive dataset is essential in matrix form. Matrix sort is an algorithm, which can sort a large amount of data in matrix form efficiently. In this paper, parallel algorithms are developed for the Matrix Sort algorithm (designed by S. Kavitha et al. Int J Comput Appl 143(9):1–6, 2016) [1]. This algorithm sorts the matrix rows and columns in parallel, subsequently applying the further procedure on resultant data. The implementations of parallel algorithms have been discussed by comparing the execution time results obtained in sequential and parallel form.

AB - Sorted data is essential. Apart from information presentation or manual retrieval of information, sorted data is beneficial even when using machines’ computational power. In many science and engineering fields, the sorting of extensive dataset is essential in matrix form. Matrix sort is an algorithm, which can sort a large amount of data in matrix form efficiently. In this paper, parallel algorithms are developed for the Matrix Sort algorithm (designed by S. Kavitha et al. Int J Comput Appl 143(9):1–6, 2016) [1]. This algorithm sorts the matrix rows and columns in parallel, subsequently applying the further procedure on resultant data. The implementations of parallel algorithms have been discussed by comparing the execution time results obtained in sequential and parallel form.

UR - http://www.scopus.com/inward/record.url?scp=85112020526&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85112020526&partnerID=8YFLogxK

U2 - 10.1007/978-981-16-1089-9_45

DO - 10.1007/978-981-16-1089-9_45

M3 - Conference contribution

AN - SCOPUS:85112020526

SN - 9789811610882

T3 - Lecture Notes in Networks and Systems

SP - 575

EP - 583

BT - Communication and Intelligent Systems - Proceedings of ICCIS 2020

A2 - Sharma, Harish

A2 - Gupta, Mukesh Kumar

A2 - Tomar, G. S.

A2 - Lipo, Wang

PB - Springer Science and Business Media Deutschland GmbH

T2 - 2nd International Conference on Communication and Intelligent Systems, ICCIS 2020

Y2 - 26 December 2020 through 27 December 2020

ER -

Parallel Matrix Sort Using MPI and CUDA

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this