Experience of FRC CSC RAS in providing high-performance computing cloud services for materials science problems

Author:

Denisov S. A.1,Volovich K. I.1,Kondrashev V. A.1

Affiliation:

1. Federal Research Center “Computer Science and Control” of the Russian Academy of Sciences

Abstract

To solve the problems of materials science, including multiscale modeling for the synthesis of materials with specified properties, a modern digital platform for scientific research has been created at the FRC CSC RAS. The digital platform is a combination of a competence center, a high-performance computing complex and a set of scientific services that are provided to researchers in the form of traditional cloud services in software (SaaS), platform (PaaS) and infrastructure (IaaS) services, as well as using specific technologies for providing researchers scientific service as a service (RaaS, Research as a Service).Other examples of scientific fields for which scientific services are used in conjunction with high-performance computing services are: biomedical chemistry, crystallography, computational linguistics, artificial intelligence.The article describes the information and computing environment of the sharing research facilities Center for Collective Use “Informatics”, which forms the basis of the instrumental and technological infrastructure for prototyping, as well as the layout of the control system for deterministic scientific services of the digital platform.The article presents the results of experimental studies carried out in relation to algorithms for the transfer and intermediate storage of initial data, data exchange services when interacting with a platform user, cloud scientific high-performance computing services, algorithms for the interaction of data exchange adapters when ensuring interaction between the platform, which are relevant in solving problems of multiscale modeling for the synthesis of materials with desired properties.The results obtained allow us to evaluate the practical aspects of the functioning of a digital platform for scientific research, designed for the effective organization of scientific research and management of the scientific instrument base in the interests of a wide range of research teams and industrial consumers.

Publisher

National University of Science and Technology MISiS

Subject

General Medicine

Reference23 articles.

1. Zatsarinnyy A. A., Kiselev E. V., Kozlov S. V., Kolin K. K. Information space of the digital economy of Russia. Conceptual foundations and problems of formation. Moscow: OOO “NIPKTs Voskhod-A”, 2018. 236 p. (In Russ.)

2. Zatsarinny A. A., Kondrashev V. A., Suchkov A. P. The system of scientific services as a relevant component of scientific research. Systems and Means of Informatics. 2019, vol. 29, iss. 1, pp. 25—40. (In Russ.). DOI: 10.14357/08696527190103

3. Zatsarinny A. A., Kondrashev V. A., Sorokin A. A. Approaches to the organization of the computing process of a hybrid high-performance computing cluster in the digital platform environment. CEUR Workshop Proc.: 5th International Conference on Information Technologies and High-Performance Computing, ITHPC 2019; Computing Center of Far East Branch of the Russian Academy of Science. Khabarovsk, 16–19 September 2019, vol. 2426. Khabarovsk, 2019. Pp. 12—16.

4. Zatsarinny A. A., Kondrashev V. A., Sorokin A. A., Denisov S. A. Scientific services consolidation methods. Izvestiya Vysshikh Uchebnykh Zavedenii. Materialy Elektronnoi Tekhniki = Materials of Electronics Engineering. 2019, vol. 22, no. 4, pp. 302—307. (In Russ.). DOI: 10.17073/1609-3577-2019-4-302-307

5. Volovich K. I., Denisov S. A. The main scientific and technical problems of using hybrid HPC clusters in materials science. Izvestiya Vysshikh Uchebnykh Zavedenii. Materialy Elektronnoi Tekhniki = Materials of Electronics Engineering. 2019, vol. 22, no. 4, pp. 262—267. (In Russ.). DOI: 10.17073/1609-3577-2019-4-262-267

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3