Characteristic Analysis of Applications for Designing a Future HPC System

Osamu Watanabe (), Takashi Soga (), Youichi Shimomura () and Akihiro Musa ()
Additional contact information
Osamu Watanabe: NEC Corporation, 1st Government and Public Solutions Division
Takashi Soga: NEC Solution Innovators
Youichi Shimomura: NEC Solution Innovators
Akihiro Musa: NEC Corporation, 1st Government and Public Solutions Division

A chapter in Sustained Simulation Performance 2014, 2015, pp 33-46 from Springer

Abstract: Abstract Computer simulations have become an effective tool for finding solutions to various social and scientific challenges: countermeasures against disasters, environmental issues, industrial competitiveness, and so on. To research future HPC systems for finding such solutions, the Ministry of Education, Culture, Sports, Science and Technology in Japan conducted a research program, “Feasibility Study of Future HPCI Systems”. Tohoku University, the Japan Agency for Marine-Earth Science and Technology, and NEC Corporation participated in the program. An application research group was formed to clarify characteristics of several application programs in the fields of natural disaster mitigation and high productivity engineering for designing a future HPC system by around 2020. In this article, we describe the overview of our research in the program.The application research group investigates characteristics of the application programs; for example, the ratio of memory bandwidth to computational performance (B∕F), calculation amount, memory capacity, MPI data traffic, and so on. Then, we clarify that the B/Fs of most researched application programs are greater than 2 B/F. Thus, these application programs are memory intensive, and the B/F in future HPC systems will need 2 B/F or greater to preserve the computational performance. Also, this group estimates the performance of the application programs on our designed future HPC system with a high memory bandwidth. Our research shows that our future HPC system has the potential to overcome the challenges of natural disaster mitigation and high productivity engineering.

Keywords: Application Program; Memory Bandwidth; Target Application; Coupling Simulation; Scientific Challenge (search for similar items in EconPapers)
Date: 2015
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-319-10626-7_3

Ordering information: This item can be ordered from
http://www.springer.com/9783319106267

DOI: 10.1007/978-3-319-10626-7_3

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().