Performance evaluation of the MODYLAS application on modern multi-core and many-core environments

Satoshi Ohshima, Soichiro Suzuki, Tatsuya Sakashita, Masao Ogino, Takahiro Katagiri, Yoshimichi Andoh

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

Abstract

Molecular dynamics (MD) simulations are an essential tool for various fields of science. To broaden the range of applications of MD simulations, faster and more large-scale simulations that achieve the same accuracy are required. Authors have developed an MD application named MODYLAS over several years. In our previous work, we focused on the pairwise additive calculation of potentials and forces, which is one of the hot spots in MD simulations. We have proposed new thread-level algorithms and evaluated the performance using the FX100 supercomputer system. In this study, we measure the performance of the above algorithms on Skylake-SP and Knights Landing processors and compare the results with FX100. Using the obtained results, we discuss the application performance on this hardware and the potential performance improvement by using the auto-tuning technique.

Original languageEnglish
Title of host publicationProceedings - 2019 IEEE 33rd International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages787-796
Number of pages10
ISBN (Electronic)9781728135106
DOIs
Publication statusPublished - May 1 2019
Event33rd IEEE International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2019 - Rio de Janeiro, Brazil
Duration: May 20 2019May 24 2019

Publication series

NameProceedings - 2019 IEEE 33rd International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2019

Conference

Conference33rd IEEE International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2019
CountryBrazil
CityRio de Janeiro
Period5/20/195/24/19

Fingerprint

Many-core
Performance Evaluation
Molecular dynamics
Molecular Dynamics Simulation
Computer simulation
Auto-tuning
Supercomputers
Supercomputer
Hot Spot
Landing
Molecular Dynamics
Thread
Pairwise
Tuning
Hardware
Dynamic simulation
Performance evaluation
Range of data
Simulation

All Science Journal Classification (ASJC) codes

  • Information Systems and Management
  • Artificial Intelligence
  • Computer Networks and Communications
  • Hardware and Architecture
  • Control and Optimization

Cite this

Ohshima, S., Suzuki, S., Sakashita, T., Ogino, M., Katagiri, T., & Andoh, Y. (2019). Performance evaluation of the MODYLAS application on modern multi-core and many-core environments. In Proceedings - 2019 IEEE 33rd International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2019 (pp. 787-796). [8778307] (Proceedings - 2019 IEEE 33rd International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IPDPSW.2019.00129

Performance evaluation of the MODYLAS application on modern multi-core and many-core environments. / Ohshima, Satoshi; Suzuki, Soichiro; Sakashita, Tatsuya; Ogino, Masao; Katagiri, Takahiro; Andoh, Yoshimichi.

Proceedings - 2019 IEEE 33rd International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 787-796 8778307 (Proceedings - 2019 IEEE 33rd International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2019).

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

Ohshima, S, Suzuki, S, Sakashita, T, Ogino, M, Katagiri, T & Andoh, Y 2019, Performance evaluation of the MODYLAS application on modern multi-core and many-core environments. in Proceedings - 2019 IEEE 33rd International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2019., 8778307, Proceedings - 2019 IEEE 33rd International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2019, Institute of Electrical and Electronics Engineers Inc., pp. 787-796, 33rd IEEE International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2019, Rio de Janeiro, Brazil, 5/20/19. https://doi.org/10.1109/IPDPSW.2019.00129
Ohshima S, Suzuki S, Sakashita T, Ogino M, Katagiri T, Andoh Y. Performance evaluation of the MODYLAS application on modern multi-core and many-core environments. In Proceedings - 2019 IEEE 33rd International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 787-796. 8778307. (Proceedings - 2019 IEEE 33rd International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2019). https://doi.org/10.1109/IPDPSW.2019.00129
Ohshima, Satoshi ; Suzuki, Soichiro ; Sakashita, Tatsuya ; Ogino, Masao ; Katagiri, Takahiro ; Andoh, Yoshimichi. / Performance evaluation of the MODYLAS application on modern multi-core and many-core environments. Proceedings - 2019 IEEE 33rd International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2019. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 787-796 (Proceedings - 2019 IEEE 33rd International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2019).
@inproceedings{348730bf88e84803a2cdf86701e3b13c,
title = "Performance evaluation of the MODYLAS application on modern multi-core and many-core environments",
abstract = "Molecular dynamics (MD) simulations are an essential tool for various fields of science. To broaden the range of applications of MD simulations, faster and more large-scale simulations that achieve the same accuracy are required. Authors have developed an MD application named MODYLAS over several years. In our previous work, we focused on the pairwise additive calculation of potentials and forces, which is one of the hot spots in MD simulations. We have proposed new thread-level algorithms and evaluated the performance using the FX100 supercomputer system. In this study, we measure the performance of the above algorithms on Skylake-SP and Knights Landing processors and compare the results with FX100. Using the obtained results, we discuss the application performance on this hardware and the potential performance improvement by using the auto-tuning technique.",
author = "Satoshi Ohshima and Soichiro Suzuki and Tatsuya Sakashita and Masao Ogino and Takahiro Katagiri and Yoshimichi Andoh",
year = "2019",
month = "5",
day = "1",
doi = "10.1109/IPDPSW.2019.00129",
language = "English",
series = "Proceedings - 2019 IEEE 33rd International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2019",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "787--796",
booktitle = "Proceedings - 2019 IEEE 33rd International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2019",
address = "United States",

}

TY - GEN

T1 - Performance evaluation of the MODYLAS application on modern multi-core and many-core environments

AU - Ohshima, Satoshi

AU - Suzuki, Soichiro

AU - Sakashita, Tatsuya

AU - Ogino, Masao

AU - Katagiri, Takahiro

AU - Andoh, Yoshimichi

PY - 2019/5/1

Y1 - 2019/5/1

N2 - Molecular dynamics (MD) simulations are an essential tool for various fields of science. To broaden the range of applications of MD simulations, faster and more large-scale simulations that achieve the same accuracy are required. Authors have developed an MD application named MODYLAS over several years. In our previous work, we focused on the pairwise additive calculation of potentials and forces, which is one of the hot spots in MD simulations. We have proposed new thread-level algorithms and evaluated the performance using the FX100 supercomputer system. In this study, we measure the performance of the above algorithms on Skylake-SP and Knights Landing processors and compare the results with FX100. Using the obtained results, we discuss the application performance on this hardware and the potential performance improvement by using the auto-tuning technique.

AB - Molecular dynamics (MD) simulations are an essential tool for various fields of science. To broaden the range of applications of MD simulations, faster and more large-scale simulations that achieve the same accuracy are required. Authors have developed an MD application named MODYLAS over several years. In our previous work, we focused on the pairwise additive calculation of potentials and forces, which is one of the hot spots in MD simulations. We have proposed new thread-level algorithms and evaluated the performance using the FX100 supercomputer system. In this study, we measure the performance of the above algorithms on Skylake-SP and Knights Landing processors and compare the results with FX100. Using the obtained results, we discuss the application performance on this hardware and the potential performance improvement by using the auto-tuning technique.

UR - http://www.scopus.com/inward/record.url?scp=85070393232&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070393232&partnerID=8YFLogxK

U2 - 10.1109/IPDPSW.2019.00129

DO - 10.1109/IPDPSW.2019.00129

M3 - Conference contribution

AN - SCOPUS:85070393232

T3 - Proceedings - 2019 IEEE 33rd International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2019

SP - 787

EP - 796

BT - Proceedings - 2019 IEEE 33rd International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2019

PB - Institute of Electrical and Electronics Engineers Inc.

ER -