• Proceedings of the Korean Society of Computational and Applied Mathematics Conference
• /
• 2003.09a
• /
• pp.5.1-5
• /
• 2003

In this paper, we study the convergence of relaxed multisplitting and relaxed nonstationary two-stage multisplitting methods associated with a multisplitting which is obtained from the ILU factorizations for solving a linear system whose coefficient matrix is an H-matrix. Also, parallel performance results of relaxed nonstaionary two-stage multisplitting method using ILU factorizations as inner splittings on the IBM p690 supercomputer are provided to analyze theoretical results.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2010.05a
• /
• pp.1121-1122
• /
• 2010

• Membrane Journal
• /
• v.3 no.3
• /
• pp.94-107
• /
• 1993

Many researchers have discussed how membrane performance can be enhanced through an understanding of polymer science and engineering. The understandings of transport in porous membrane are used to achieve the isolation of certain components from mixtures. Particular emphasis is placed on the applicability of membrane separations for the isolation of macromolecules[1]. An awareness of membrane structure characteristics is required for the rational design of membranes for specific and/or new applications. This understanding rests on the knowledge of fields such as polymer thermodynamics[2], polymer adsorption [3, 4], diffusion in polymers[5, 6], reaction mechanism[7], and the dynamic behavior[8, 9] of polymer in porous membrane.

• Journal of applied mathematics & informatics
• /
• v.15 no.1_2
• /
• pp.77-90
• /
• 2004

In this paper, we study the convergence of both relaxed multisplitting method and nonstationary two-stage multisplitting method associated with a multisplitting which is obtained from the ILU factorizations for solving a linear system whose coefficient matrix is an H-matrix. Also, parallel performance results of nonstaionary two-stage multisplitting method using ILU factorizations as inner splittings on the IBM p690 supercomputer are provided to analyze theoretical results.

• Journal of computational fluids engineering
• /
• v.6 no.3
• /
• pp.51-56
• /
• 2001

As IT(Information Technology) has been developing, an application engineering is advanced so quickly. Especially, CFD field that is influenced greatly by Computing Power is an outstanding example. In this paper, it says a research tendency of the KISTI Supercomputing Center that performs the CFD research based on IT. The representative researches are the National Grid Project, TeraCluster Construction and development and a supporting plan for Supercomputer users' parallelization.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.11a
• /
• pp.159-160
• /
• 2009

하드웨어 기술이 발전하면서 단위 노드당 집적되는 CPU 수와 메모리량이 증가되어 단위 시스템의 성능이 크게 개선되었다. HPC 시스템도 SMP 시스템과 같은 고성능 노드를 사용하는 클러스터 시스템 위주로 발전하게 되었다. 본 연구에서는 IBM Power 595 기반 슈퍼컴퓨터에서 집합 통신이 갖는 특성을 알아 본다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.109-112
• /
• 2021

매년 슈퍼컴퓨터를 표적으로 공격이 증가하고 있고, 공격의 방식은 날로 진화하고 있다. 슈퍼컴퓨터를 대상으로 하는 공격에 대응하기 위해 기존의 연구는 공격 특성을 분석하여 맞춤형 대책을 제시하거나 분석을 통해 보안 요구사항을 도출하였다. 하지만 연구과정에서 APT life cycle 관점이 반영되지 않으면, 지능형 지속 위협인 APT를 인지 및 대응하기 어려운 문제점이 있다. 이러한 문제점을 해결하기 위해, 본 논문은 APT 시나리오 기반의 위협 모델링 분석을 통해 슈퍼컴퓨터 보안 요구사항을 도출 한다.

• Journal of the Korea Convergence Society
• /
• v.8 no.11
• /
• pp.21-27
• /
• 2017

Internet of Things(IoT), which is developing for the hyper connection society, is based on OSHW (Open Source Hardware) such as Arduino and various small products are emerging. Because of the limitation of low performance and low memory, the IoT is causing serious information security problem that it is difficult to apply strong security technology. In this paper, we analyze the vulnerability that can occur as a result of compiling and loading the application program of Arduino on the host computer. And we propose a new attack method that allows an attacker to arbitrarily change the value input from the sensor of the arduino board. Such as a proposed attack method may cause the arduino board to misinterpret environmental information and render it inoperable. By understanding these attack techniques, it is possible to consider how to build a secure development environment and cope with these attacks.

• Journal of the Korea Convergence Society
• /
• v.8 no.11
• /
• pp.63-69
• /
• 2017

The middleware in the IoT system is software that acts as a messenger to connect and exchange data between humans and objects, objects and objects. IoT middleware exists in various forms in all areas, including hardware, protocol, and communication of different kinds, which are different in form and purpose. However, IoT middleware exists in various forms across different areas, including hardware, protocol, and communication of different types and purposes. Therefore, even if the system is designed differently for each role, it is necessary to strengthen the security in common. In this paper, we analyze the structure of IoT middleware using Service Oriented Architecture(SOA) approach and design system security requirements based on it. It was defined: Target Of Evaluation(TOE) existing system development method and the object is evaluated by Common Criteria(CC) for verification based otherwise. The proposed middleware system will be correlated with the security problem definition and the security purpose, which will be the basis for implementing the security enhanced IoT system.

• Journal of Digital Contents Society
• /
• v.16 no.5
• /
• pp.691-697
• /
• 2015

Supercomputers are used for many different areas including new product design of industries as well as state-of-the-art science and technology for large amount of computational needs. Tachyon is a 4th supercomputer built at KISTI that is a high-performance parallel computing system with 3,200 computing nodes and infrastructures. This system is currently about 10,000 users and over 170 organizations are used, the number of jobs they are performing work in batch type form through a scheduler. Also, this system logs lots of job scripts, execution environment, library, job status from the job submit to end. In this paper, we analyzed batch jobs information from Sun Grid Engine, that use as a scheduler in Tachyon system, and job executed information in Tachyon System. In particular, we distinguished the fail jobs from the all tasks that users perform and we analyzed the cause of failure. Among them, we can extracted some of jobs that can be regarded as normal jobs through the improvement in those works logged as all of fail jobs.