GPU Computing for Compute-Intensive Scientific Calculation

Sandhya Parasnath Dubey, M. Sathish Kumar, S. Balaji

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

Abstract

GPU has emerged as a platform that off-loads computation intensive work from CPU and performs numerical computations in less time. One such mathematical operation is matrix multiplication. Matrix is one of the fundamental mathematical objects used in the scientific calculation, with applicability in various fields such as computer graphics, analysis of electrical circuits, computer networks, DNA sequence comparison, protein structure prediction, etc. This work presents a comparative analysis of scalar matrix multiplication in three modes, namely: (i) sequential programming in C language (ii) parallel implementations using OpenCL, and (iii) MPI. The testbed comprises of input matrices ranging from small size of 100 × 100 to a higher size of 800 × 12,800. We observe that parallel execution in OpenCL outperforms MPI and sequential C for higher dimensional matrices. In contrast, sequential C outperforms both MPI and OpenCL for small dimension matrices. Besides, we analyze that OpenCL program has attained a speedup of 9 ×. Therefore, we conclude that parallel execution of code is more efficient for data of computationally large sizes and hence provides a potentially useful solution to address NP-complete problems.

Original languageEnglish
Title of host publicationSoft Computing for Problem Solving SocProS 2018, Volume 2
EditorsKedar Nath Das, Jagdish Chand Bansal, Kusum Deep, Atulya K. Nagar, Ponnambalam Pathipooranam, Rani Chinnappa Naidu
PublisherSpringer Paris
Pages131-140
Number of pages10
ISBN (Print)9789811501838
DOIs
Publication statusPublished - 01-01-2020
Event8th International Conference on Soft Computing for Problem Solving, SocProS 2018 - Vellore, India
Duration: 17-12-201819-12-2018

Publication series

NameAdvances in Intelligent Systems and Computing
Volume1057
ISSN (Print)2194-5357
ISSN (Electronic)2194-5365

Conference

Conference8th International Conference on Soft Computing for Problem Solving, SocProS 2018
CountryIndia
CityVellore
Period17-12-1819-12-18

Fingerprint

DNA sequences
Computer graphics
Computer networks
Testbeds
Program processors
Graphics processing unit
Computational complexity
Proteins
Networks (circuits)

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Computer Science(all)

Cite this

Dubey, S. P., Kumar, M. S., & Balaji, S. (2020). GPU Computing for Compute-Intensive Scientific Calculation. In K. N. Das, J. C. Bansal, K. Deep, A. K. Nagar, P. Pathipooranam, & R. C. Naidu (Eds.), Soft Computing for Problem Solving SocProS 2018, Volume 2 (pp. 131-140). (Advances in Intelligent Systems and Computing; Vol. 1057). Springer Paris. https://doi.org/10.1007/978-981-15-0184-5_12
Dubey, Sandhya Parasnath ; Kumar, M. Sathish ; Balaji, S. / GPU Computing for Compute-Intensive Scientific Calculation. Soft Computing for Problem Solving SocProS 2018, Volume 2. editor / Kedar Nath Das ; Jagdish Chand Bansal ; Kusum Deep ; Atulya K. Nagar ; Ponnambalam Pathipooranam ; Rani Chinnappa Naidu. Springer Paris, 2020. pp. 131-140 (Advances in Intelligent Systems and Computing).
@inproceedings{c14e005eadb24bcf97764be6a492db5a,
title = "GPU Computing for Compute-Intensive Scientific Calculation",
abstract = "GPU has emerged as a platform that off-loads computation intensive work from CPU and performs numerical computations in less time. One such mathematical operation is matrix multiplication. Matrix is one of the fundamental mathematical objects used in the scientific calculation, with applicability in various fields such as computer graphics, analysis of electrical circuits, computer networks, DNA sequence comparison, protein structure prediction, etc. This work presents a comparative analysis of scalar matrix multiplication in three modes, namely: (i) sequential programming in C language (ii) parallel implementations using OpenCL, and (iii) MPI. The testbed comprises of input matrices ranging from small size of 100 × 100 to a higher size of 800 × 12,800. We observe that parallel execution in OpenCL outperforms MPI and sequential C for higher dimensional matrices. In contrast, sequential C outperforms both MPI and OpenCL for small dimension matrices. Besides, we analyze that OpenCL program has attained a speedup of 9 ×. Therefore, we conclude that parallel execution of code is more efficient for data of computationally large sizes and hence provides a potentially useful solution to address NP-complete problems.",
author = "Dubey, {Sandhya Parasnath} and Kumar, {M. Sathish} and S. Balaji",
year = "2020",
month = "1",
day = "1",
doi = "10.1007/978-981-15-0184-5_12",
language = "English",
isbn = "9789811501838",
series = "Advances in Intelligent Systems and Computing",
publisher = "Springer Paris",
pages = "131--140",
editor = "Das, {Kedar Nath} and Bansal, {Jagdish Chand} and Kusum Deep and Nagar, {Atulya K.} and Ponnambalam Pathipooranam and Naidu, {Rani Chinnappa}",
booktitle = "Soft Computing for Problem Solving SocProS 2018, Volume 2",
address = "France",

}

Dubey, SP, Kumar, MS & Balaji, S 2020, GPU Computing for Compute-Intensive Scientific Calculation. in KN Das, JC Bansal, K Deep, AK Nagar, P Pathipooranam & RC Naidu (eds), Soft Computing for Problem Solving SocProS 2018, Volume 2. Advances in Intelligent Systems and Computing, vol. 1057, Springer Paris, pp. 131-140, 8th International Conference on Soft Computing for Problem Solving, SocProS 2018, Vellore, India, 17-12-18. https://doi.org/10.1007/978-981-15-0184-5_12

GPU Computing for Compute-Intensive Scientific Calculation. / Dubey, Sandhya Parasnath; Kumar, M. Sathish; Balaji, S.

Soft Computing for Problem Solving SocProS 2018, Volume 2. ed. / Kedar Nath Das; Jagdish Chand Bansal; Kusum Deep; Atulya K. Nagar; Ponnambalam Pathipooranam; Rani Chinnappa Naidu. Springer Paris, 2020. p. 131-140 (Advances in Intelligent Systems and Computing; Vol. 1057).

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

TY - GEN

T1 - GPU Computing for Compute-Intensive Scientific Calculation

AU - Dubey, Sandhya Parasnath

AU - Kumar, M. Sathish

AU - Balaji, S.

PY - 2020/1/1

Y1 - 2020/1/1

N2 - GPU has emerged as a platform that off-loads computation intensive work from CPU and performs numerical computations in less time. One such mathematical operation is matrix multiplication. Matrix is one of the fundamental mathematical objects used in the scientific calculation, with applicability in various fields such as computer graphics, analysis of electrical circuits, computer networks, DNA sequence comparison, protein structure prediction, etc. This work presents a comparative analysis of scalar matrix multiplication in three modes, namely: (i) sequential programming in C language (ii) parallel implementations using OpenCL, and (iii) MPI. The testbed comprises of input matrices ranging from small size of 100 × 100 to a higher size of 800 × 12,800. We observe that parallel execution in OpenCL outperforms MPI and sequential C for higher dimensional matrices. In contrast, sequential C outperforms both MPI and OpenCL for small dimension matrices. Besides, we analyze that OpenCL program has attained a speedup of 9 ×. Therefore, we conclude that parallel execution of code is more efficient for data of computationally large sizes and hence provides a potentially useful solution to address NP-complete problems.

AB - GPU has emerged as a platform that off-loads computation intensive work from CPU and performs numerical computations in less time. One such mathematical operation is matrix multiplication. Matrix is one of the fundamental mathematical objects used in the scientific calculation, with applicability in various fields such as computer graphics, analysis of electrical circuits, computer networks, DNA sequence comparison, protein structure prediction, etc. This work presents a comparative analysis of scalar matrix multiplication in three modes, namely: (i) sequential programming in C language (ii) parallel implementations using OpenCL, and (iii) MPI. The testbed comprises of input matrices ranging from small size of 100 × 100 to a higher size of 800 × 12,800. We observe that parallel execution in OpenCL outperforms MPI and sequential C for higher dimensional matrices. In contrast, sequential C outperforms both MPI and OpenCL for small dimension matrices. Besides, we analyze that OpenCL program has attained a speedup of 9 ×. Therefore, we conclude that parallel execution of code is more efficient for data of computationally large sizes and hence provides a potentially useful solution to address NP-complete problems.

UR - http://www.scopus.com/inward/record.url?scp=85076828734&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85076828734&partnerID=8YFLogxK

U2 - 10.1007/978-981-15-0184-5_12

DO - 10.1007/978-981-15-0184-5_12

M3 - Conference contribution

AN - SCOPUS:85076828734

SN - 9789811501838

T3 - Advances in Intelligent Systems and Computing

SP - 131

EP - 140

BT - Soft Computing for Problem Solving SocProS 2018, Volume 2

A2 - Das, Kedar Nath

A2 - Bansal, Jagdish Chand

A2 - Deep, Kusum

A2 - Nagar, Atulya K.

A2 - Pathipooranam, Ponnambalam

A2 - Naidu, Rani Chinnappa

PB - Springer Paris

ER -

Dubey SP, Kumar MS, Balaji S. GPU Computing for Compute-Intensive Scientific Calculation. In Das KN, Bansal JC, Deep K, Nagar AK, Pathipooranam P, Naidu RC, editors, Soft Computing for Problem Solving SocProS 2018, Volume 2. Springer Paris. 2020. p. 131-140. (Advances in Intelligent Systems and Computing). https://doi.org/10.1007/978-981-15-0184-5_12