A co-design study of fusion whole device modeling using code coupling

Jong Youl Choi; Matthew Wolf; Scott Klasky; Jeremy Logan; Kshitij Mehta; Eric Suchyta; William Godoy; Nick Thompson; Lipeng Wan; Jieyang Chen; Norbert Podhorszki; Julien Dominski; Choong Seock Chang

doi:10.1109/DRBSD-549595.2019.00011

A co-design study of fusion whole device modeling using code coupling

Jong Youl Choi, Matthew Wolf, Scott Klasky, Jeremy Logan, Kshitij Mehta, Eric Suchyta, William Godoy, Nick Thompson, Lipeng Wan, Jieyang Chen, Norbert Podhorszki, Julien Dominski, Choong Seock Chang

PPPL Theory

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

2 Scopus citations

Abstract

Complex workflows consisting of multiple simulation and analysis codes running concurrently through in-memory coupling is becoming popular due to inherent advantages in online management of large-scale data, resilience, and the code development process. However, orchestrating such a multi-application workflow to efficiently utilize resources on a heterogeneous architecture is challenging. In this paper, we present our results with running the Fusion Whole Device Modeling benchmark workflow on Summit, a pre-exascale supercomputer at Oak Ridge National Laboratory. We explore various resource distribution and process placement mechanisms, including sharing compute nodes between processes from separate applications. We show that fine-grained process placement can have a significant impact towards efficient utilization of the compute power of a node on Summit, and conclude that sophisticated tools for performing co-design studies of multi-application workflows can play an important role towards efficient orchestration of such workflows.

Original language	English (US)
Title of host publication	Proceedings of DRBSD-5 2019
Subtitle of host publication	5th International Workshop on Data Analysis and Reduction for Big Scientific Data - Held in conjunction with SC 2019: The International Conference for High Performance Computing, Networking, Storage and Analysis
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	35-41
Number of pages	7
ISBN (Electronic)	9781728160177
DOIs	https://doi.org/10.1109/DRBSD-549595.2019.00011
State	Published - Nov 2019
Event	5th IEEE/ACM International Workshop on Data Analysis and Reduction for Big Scientific Data, DRBSD-5 2019 - Denver, United States Duration: Nov 17 2019 → …

Publication series

Name	Proceedings of DRBSD-5 2019: 5th International Workshop on Data Analysis and Reduction for Big Scientific Data - Held in conjunction with SC 2019: The International Conference for High Performance Computing, Networking, Storage and Analysis

Conference

Conference	5th IEEE/ACM International Workshop on Data Analysis and Reduction for Big Scientific Data, DRBSD-5 2019
Country/Territory	United States
City	Denver
Period	11/17/19 → …

All Science Journal Classification (ASJC) codes

Media Technology
Artificial Intelligence
Information Systems
Information Systems and Management
Statistics, Probability and Uncertainty

Keywords

Co-design
Coupling
Fusion
Summit
Whole device model
Workflow

Access to Document

10.1109/DRBSD-549595.2019.00011

Cite this

Choi, J. Y., Wolf, M., Klasky, S., Logan, J., Mehta, K., Suchyta, E., Godoy, W., Thompson, N., Wan, L., Chen, J., Podhorszki, N., Dominski, J., & Chang, C. S. (2019). A co-design study of fusion whole device modeling using code coupling. In Proceedings of DRBSD-5 2019: 5th International Workshop on Data Analysis and Reduction for Big Scientific Data - Held in conjunction with SC 2019: The International Conference for High Performance Computing, Networking, Storage and Analysis (pp. 35-41). Article 8955116 (Proceedings of DRBSD-5 2019: 5th International Workshop on Data Analysis and Reduction for Big Scientific Data - Held in conjunction with SC 2019: The International Conference for High Performance Computing, Networking, Storage and Analysis). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/DRBSD-549595.2019.00011

Choi, Jong Youl ; Wolf, Matthew ; Klasky, Scott et al. / A co-design study of fusion whole device modeling using code coupling. Proceedings of DRBSD-5 2019: 5th International Workshop on Data Analysis and Reduction for Big Scientific Data - Held in conjunction with SC 2019: The International Conference for High Performance Computing, Networking, Storage and Analysis. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 35-41 (Proceedings of DRBSD-5 2019: 5th International Workshop on Data Analysis and Reduction for Big Scientific Data - Held in conjunction with SC 2019: The International Conference for High Performance Computing, Networking, Storage and Analysis).

@inproceedings{e4bfe020f2fb4390aa96ce6d48fc5feb,

title = "A co-design study of fusion whole device modeling using code coupling",

abstract = "Complex workflows consisting of multiple simulation and analysis codes running concurrently through in-memory coupling is becoming popular due to inherent advantages in online management of large-scale data, resilience, and the code development process. However, orchestrating such a multi-application workflow to efficiently utilize resources on a heterogeneous architecture is challenging. In this paper, we present our results with running the Fusion Whole Device Modeling benchmark workflow on Summit, a pre-exascale supercomputer at Oak Ridge National Laboratory. We explore various resource distribution and process placement mechanisms, including sharing compute nodes between processes from separate applications. We show that fine-grained process placement can have a significant impact towards efficient utilization of the compute power of a node on Summit, and conclude that sophisticated tools for performing co-design studies of multi-application workflows can play an important role towards efficient orchestration of such workflows.",

keywords = "Co-design, Coupling, Fusion, Summit, Whole device model, Workflow",

author = "Choi, \{Jong Youl\} and Matthew Wolf and Scott Klasky and Jeremy Logan and Kshitij Mehta and Eric Suchyta and William Godoy and Nick Thompson and Lipeng Wan and Jieyang Chen and Norbert Podhorszki and Julien Dominski and Chang, \{Choong Seock\}",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 5th IEEE/ACM International Workshop on Data Analysis and Reduction for Big Scientific Data, DRBSD-5 2019 ; Conference date: 17-11-2019",

year = "2019",

month = nov,

doi = "10.1109/DRBSD-549595.2019.00011",

language = "English (US)",

series = "Proceedings of DRBSD-5 2019: 5th International Workshop on Data Analysis and Reduction for Big Scientific Data - Held in conjunction with SC 2019: The International Conference for High Performance Computing, Networking, Storage and Analysis",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "35--41",

booktitle = "Proceedings of DRBSD-5 2019",

address = "United States",

}

Choi, JY, Wolf, M, Klasky, S, Logan, J, Mehta, K, Suchyta, E, Godoy, W, Thompson, N, Wan, L, Chen, J, Podhorszki, N, Dominski, J & Chang, CS 2019, A co-design study of fusion whole device modeling using code coupling. in Proceedings of DRBSD-5 2019: 5th International Workshop on Data Analysis and Reduction for Big Scientific Data - Held in conjunction with SC 2019: The International Conference for High Performance Computing, Networking, Storage and Analysis., 8955116, Proceedings of DRBSD-5 2019: 5th International Workshop on Data Analysis and Reduction for Big Scientific Data - Held in conjunction with SC 2019: The International Conference for High Performance Computing, Networking, Storage and Analysis, Institute of Electrical and Electronics Engineers Inc., pp. 35-41, 5th IEEE/ACM International Workshop on Data Analysis and Reduction for Big Scientific Data, DRBSD-5 2019, Denver, United States, 11/17/19. https://doi.org/10.1109/DRBSD-549595.2019.00011

A co-design study of fusion whole device modeling using code coupling. / Choi, Jong Youl; Wolf, Matthew; Klasky, Scott et al.
Proceedings of DRBSD-5 2019: 5th International Workshop on Data Analysis and Reduction for Big Scientific Data - Held in conjunction with SC 2019: The International Conference for High Performance Computing, Networking, Storage and Analysis. Institute of Electrical and Electronics Engineers Inc., 2019. p. 35-41 8955116 (Proceedings of DRBSD-5 2019: 5th International Workshop on Data Analysis and Reduction for Big Scientific Data - Held in conjunction with SC 2019: The International Conference for High Performance Computing, Networking, Storage and Analysis).

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

TY - GEN

T1 - A co-design study of fusion whole device modeling using code coupling

AU - Choi, Jong Youl

AU - Wolf, Matthew

AU - Klasky, Scott

AU - Logan, Jeremy

AU - Mehta, Kshitij

AU - Suchyta, Eric

AU - Godoy, William

AU - Thompson, Nick

AU - Wan, Lipeng

AU - Chen, Jieyang

AU - Podhorszki, Norbert

AU - Dominski, Julien

AU - Chang, Choong Seock

PY - 2019/11

Y1 - 2019/11

N2 - Complex workflows consisting of multiple simulation and analysis codes running concurrently through in-memory coupling is becoming popular due to inherent advantages in online management of large-scale data, resilience, and the code development process. However, orchestrating such a multi-application workflow to efficiently utilize resources on a heterogeneous architecture is challenging. In this paper, we present our results with running the Fusion Whole Device Modeling benchmark workflow on Summit, a pre-exascale supercomputer at Oak Ridge National Laboratory. We explore various resource distribution and process placement mechanisms, including sharing compute nodes between processes from separate applications. We show that fine-grained process placement can have a significant impact towards efficient utilization of the compute power of a node on Summit, and conclude that sophisticated tools for performing co-design studies of multi-application workflows can play an important role towards efficient orchestration of such workflows.

AB - Complex workflows consisting of multiple simulation and analysis codes running concurrently through in-memory coupling is becoming popular due to inherent advantages in online management of large-scale data, resilience, and the code development process. However, orchestrating such a multi-application workflow to efficiently utilize resources on a heterogeneous architecture is challenging. In this paper, we present our results with running the Fusion Whole Device Modeling benchmark workflow on Summit, a pre-exascale supercomputer at Oak Ridge National Laboratory. We explore various resource distribution and process placement mechanisms, including sharing compute nodes between processes from separate applications. We show that fine-grained process placement can have a significant impact towards efficient utilization of the compute power of a node on Summit, and conclude that sophisticated tools for performing co-design studies of multi-application workflows can play an important role towards efficient orchestration of such workflows.

KW - Co-design

KW - Coupling

KW - Fusion

KW - Summit

KW - Whole device model

KW - Workflow

UR - https://www.scopus.com/pages/publications/85078950755

UR - https://www.scopus.com/inward/citedby.url?scp=85078950755&partnerID=8YFLogxK

U2 - 10.1109/DRBSD-549595.2019.00011

DO - 10.1109/DRBSD-549595.2019.00011

M3 - Conference contribution

AN - SCOPUS:85078950755

T3 - Proceedings of DRBSD-5 2019: 5th International Workshop on Data Analysis and Reduction for Big Scientific Data - Held in conjunction with SC 2019: The International Conference for High Performance Computing, Networking, Storage and Analysis

SP - 35

EP - 41

BT - Proceedings of DRBSD-5 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 5th IEEE/ACM International Workshop on Data Analysis and Reduction for Big Scientific Data, DRBSD-5 2019

Y2 - 17 November 2019

ER -

Choi JY, Wolf M, Klasky S, Logan J, Mehta K, Suchyta E et al. A co-design study of fusion whole device modeling using code coupling. In Proceedings of DRBSD-5 2019: 5th International Workshop on Data Analysis and Reduction for Big Scientific Data - Held in conjunction with SC 2019: The International Conference for High Performance Computing, Networking, Storage and Analysis. Institute of Electrical and Electronics Engineers Inc. 2019. p. 35-41. 8955116. (Proceedings of DRBSD-5 2019: 5th International Workshop on Data Analysis and Reduction for Big Scientific Data - Held in conjunction with SC 2019: The International Conference for High Performance Computing, Networking, Storage and Analysis). doi: 10.1109/DRBSD-549595.2019.00011

A co-design study of fusion whole device modeling using code coupling

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Keywords

Access to Document

Other files and links

Fingerprint

Cite this