DeepThermo: Deep Learning Accelerated Parallel Monte Carlo Sampling for Thermodynamics Evaluation of High Entropy Alloys

Junqi Yin; Feiyi Wang; Mallikarjun Arjun Shankar

doi:10.1109/IPDPS54959.2023.00041

DeepThermo: Deep Learning Accelerated Parallel Monte Carlo Sampling for Thermodynamics Evaluation of High Entropy Alloys

Junqi Yin, Feiyi Wang, Mallikarjun Arjun Shankar

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

2 Scopus citations

Abstract

Since the introduction of Metropolis Monte Carlo (MC) sampling, it and its variants have become standard tools used for thermodynamics evaluations of physical systems. However, a long-standing problem that hinders the effectiveness and efficiency of MC sampling is the lack of a generic method (a.k.a. MC proposal) to update the system configurations. Consequently, current practices are not scalable. Here we propose a parallel MC sampling framework for thermodynamics evaluation - DeepThermo. By using deep learning-based MC proposals that can globally update the system configurations, we show that DeepThermo can effectively evaluate the phase transition behaviors of high entropy alloys, which have an astronomical configuration space. For the first time, we directly evaluate a density of states expanding over a range of ~e10,000 for a real material. We also demonstrate DeepThermo's performance and scalability up to 3,000 GPUs on both NVIDIA V100 and AMD MI250X-based supercomputers.

Original language	English
Title of host publication	Proceedings - 2023 IEEE International Parallel and Distributed Processing Symposium, IPDPS 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	333-343
Number of pages	11
ISBN (Electronic)	9798350337662
DOIs	https://doi.org/10.1109/IPDPS54959.2023.00041
State	Published - 2023
Event	37th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2023 - St. Petersburg, United States Duration: May 15 2023 → May 19 2023

Publication series

Name	Proceedings - 2023 IEEE International Parallel and Distributed Processing Symposium, IPDPS 2023

Conference

Conference	37th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2023
Country/Territory	United States
City	St. Petersburg
Period	05/15/23 → 05/19/23

Funding

This research was sponsored by and used resources of the Oak Ridge Leadership Computing Facility (OLCF), which is a DOE Office of Science User Facility at the Oak Ridge National Laboratory supported by the U.S. Department of Energy under Contract No. DE-AC05-00OR22725. This manuscript has been co-authored by UT-Battelle, LLC, under contract DE-AC05-00OR22725 with the US Department of Energy (DOE). The US government retains and the publisher, by accepting the article for publication, acknowledges that the US government retains a nonexclusive, paid-up, irrevocable, worldwide license to publish or reproduce the published form of this manuscript, or allow others to do so, for US government purposes. DOE will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan (http://energy.gov/downloads/doe-public-access-plan).

Keywords

Deep Learning
High Entropy Alloy
Monte Carlo Method

Access to Document

10.1109/IPDPS54959.2023.00041

Cite this

Yin, J., Wang, F., & Shankar, M. A. (2023). DeepThermo: Deep Learning Accelerated Parallel Monte Carlo Sampling for Thermodynamics Evaluation of High Entropy Alloys. In Proceedings - 2023 IEEE International Parallel and Distributed Processing Symposium, IPDPS 2023 (pp. 333-343). (Proceedings - 2023 IEEE International Parallel and Distributed Processing Symposium, IPDPS 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IPDPS54959.2023.00041

Yin, Junqi ; Wang, Feiyi ; Shankar, Mallikarjun Arjun. / DeepThermo : Deep Learning Accelerated Parallel Monte Carlo Sampling for Thermodynamics Evaluation of High Entropy Alloys. Proceedings - 2023 IEEE International Parallel and Distributed Processing Symposium, IPDPS 2023. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 333-343 (Proceedings - 2023 IEEE International Parallel and Distributed Processing Symposium, IPDPS 2023).

@inproceedings{21497c1c1b1e4b09a5e797e8217b497c,

title = "DeepThermo: Deep Learning Accelerated Parallel Monte Carlo Sampling for Thermodynamics Evaluation of High Entropy Alloys",

abstract = "Since the introduction of Metropolis Monte Carlo (MC) sampling, it and its variants have become standard tools used for thermodynamics evaluations of physical systems. However, a long-standing problem that hinders the effectiveness and efficiency of MC sampling is the lack of a generic method (a.k.a. MC proposal) to update the system configurations. Consequently, current practices are not scalable. Here we propose a parallel MC sampling framework for thermodynamics evaluation - DeepThermo. By using deep learning-based MC proposals that can globally update the system configurations, we show that DeepThermo can effectively evaluate the phase transition behaviors of high entropy alloys, which have an astronomical configuration space. For the first time, we directly evaluate a density of states expanding over a range of ~e10,000 for a real material. We also demonstrate DeepThermo's performance and scalability up to 3,000 GPUs on both NVIDIA V100 and AMD MI250X-based supercomputers.",

keywords = "Deep Learning, High Entropy Alloy, Monte Carlo Method",

author = "Junqi Yin and Feiyi Wang and Shankar, {Mallikarjun Arjun}",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 37th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2023 ; Conference date: 15-05-2023 Through 19-05-2023",

year = "2023",

doi = "10.1109/IPDPS54959.2023.00041",

language = "English",

series = "Proceedings - 2023 IEEE International Parallel and Distributed Processing Symposium, IPDPS 2023",

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

pages = "333--343",

booktitle = "Proceedings - 2023 IEEE International Parallel and Distributed Processing Symposium, IPDPS 2023",

}

Yin, J , Wang, F & Shankar, MA 2023, DeepThermo: Deep Learning Accelerated Parallel Monte Carlo Sampling for Thermodynamics Evaluation of High Entropy Alloys. in Proceedings - 2023 IEEE International Parallel and Distributed Processing Symposium, IPDPS 2023. Proceedings - 2023 IEEE International Parallel and Distributed Processing Symposium, IPDPS 2023, Institute of Electrical and Electronics Engineers Inc., pp. 333-343, 37th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2023, St. Petersburg, United States, 05/15/23. https://doi.org/10.1109/IPDPS54959.2023.00041

DeepThermo: Deep Learning Accelerated Parallel Monte Carlo Sampling for Thermodynamics Evaluation of High Entropy Alloys. / Yin, Junqi ; Wang, Feiyi ; Shankar, Mallikarjun Arjun.
Proceedings - 2023 IEEE International Parallel and Distributed Processing Symposium, IPDPS 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 333-343 (Proceedings - 2023 IEEE International Parallel and Distributed Processing Symposium, IPDPS 2023).

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

TY - GEN

T1 - DeepThermo

T2 - 37th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2023

AU - Yin, Junqi

AU - Wang, Feiyi

AU - Shankar, Mallikarjun Arjun

PY - 2023

Y1 - 2023

N2 - Since the introduction of Metropolis Monte Carlo (MC) sampling, it and its variants have become standard tools used for thermodynamics evaluations of physical systems. However, a long-standing problem that hinders the effectiveness and efficiency of MC sampling is the lack of a generic method (a.k.a. MC proposal) to update the system configurations. Consequently, current practices are not scalable. Here we propose a parallel MC sampling framework for thermodynamics evaluation - DeepThermo. By using deep learning-based MC proposals that can globally update the system configurations, we show that DeepThermo can effectively evaluate the phase transition behaviors of high entropy alloys, which have an astronomical configuration space. For the first time, we directly evaluate a density of states expanding over a range of ~e10,000 for a real material. We also demonstrate DeepThermo's performance and scalability up to 3,000 GPUs on both NVIDIA V100 and AMD MI250X-based supercomputers.

AB - Since the introduction of Metropolis Monte Carlo (MC) sampling, it and its variants have become standard tools used for thermodynamics evaluations of physical systems. However, a long-standing problem that hinders the effectiveness and efficiency of MC sampling is the lack of a generic method (a.k.a. MC proposal) to update the system configurations. Consequently, current practices are not scalable. Here we propose a parallel MC sampling framework for thermodynamics evaluation - DeepThermo. By using deep learning-based MC proposals that can globally update the system configurations, we show that DeepThermo can effectively evaluate the phase transition behaviors of high entropy alloys, which have an astronomical configuration space. For the first time, we directly evaluate a density of states expanding over a range of ~e10,000 for a real material. We also demonstrate DeepThermo's performance and scalability up to 3,000 GPUs on both NVIDIA V100 and AMD MI250X-based supercomputers.

KW - Deep Learning

KW - High Entropy Alloy

KW - Monte Carlo Method

UR - http://www.scopus.com/inward/record.url?scp=85166654266&partnerID=8YFLogxK

U2 - 10.1109/IPDPS54959.2023.00041

DO - 10.1109/IPDPS54959.2023.00041

M3 - Conference contribution

AN - SCOPUS:85166654266

T3 - Proceedings - 2023 IEEE International Parallel and Distributed Processing Symposium, IPDPS 2023

SP - 333

EP - 343

BT - Proceedings - 2023 IEEE International Parallel and Distributed Processing Symposium, IPDPS 2023

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 15 May 2023 through 19 May 2023

ER -

Yin J , Wang F , Shankar MA. DeepThermo: Deep Learning Accelerated Parallel Monte Carlo Sampling for Thermodynamics Evaluation of High Entropy Alloys. In Proceedings - 2023 IEEE International Parallel and Distributed Processing Symposium, IPDPS 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 333-343. (Proceedings - 2023 IEEE International Parallel and Distributed Processing Symposium, IPDPS 2023). doi: 10.1109/IPDPS54959.2023.00041

DeepThermo: Deep Learning Accelerated Parallel Monte Carlo Sampling for Thermodynamics Evaluation of High Entropy Alloys

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this