• KIISE Transactions on Computing Practices
• /
• v.22 no.4
• /
• pp.163-169
• /
• 2016

Lustre is a scalable, distributed file system, which is popular in the field of high-performance computing. Recently, the advent of SSD has enabled high-performance storage hardware, but software development requires further improvement. In this paper, we analyzed performance of the Lustre system using SSD via extensive experimentation. We compared performance of Lustre on SSDs and HDDs in terms of file read/write throughputs and metadata access latencies. Our experimental results showed that 1) SSDs improve metadata access performance due to fast random read/write access of SSD characteristics, and 2) SSD are benefited to a greater extent under multiple threads and large numbers of small sized files.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.80-82
• /
• 2020

전통적으로 기초 과학 분야의 대규모 워크로드 작업들은 슈퍼컴퓨터와 같은 대용량 클러스터 시스템을 이용하여 수행해왔다. 그러나 최근 빅데이터 및 머신 러닝과 같은 새로운 분야에서의 컴퓨팅 자원 요구가 증가하고 기존 사용자의 요구 사항도 다양해짐에 따라 기존의 클러스터 시스템 운영 환경에서는 많은 어려움이 나타나고 있다. 이러한 문제를 해결하기 위해 한국과학기술정보연구원(KISTI)에서는 지난 3 월부터 KI (KISTI Intelligent) Cloud 서비스를 개발하여 서비스를 제공하고 있다. KI Cloud 서비스는 다음과 같은 특징이 있다. 첫째, Jupyter 과 RStudio 와 같은 대화형 개발 환경을 웹을 통해 제공함으로써 사용자는 언제, 어디서나 손쉽게 서비스를 활용할 수 있다. 둘째, 컨테이너 기술을 활용하여 사용자가 요구하는 개발 및 실행 환경을 실시간으로 구성하여 제공한다. 셋째, 사용자의 서비스 환경을 동적으로 구성하여 제공함으로써 컴퓨팅 자원의 효율성을 높일 수 있다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.1
• /
• pp.138-144
• /
• 2010

Tachyon primary system which introduces recently is a high performance supercomputer that composed with AMD Barcelona nodes. In this paper, we will verify the performance and parallel scalability of TachyonIn by using multi-zone NAS Parallel Benchmark(NPB) which is one of a program with hybrid parallel method. To test performance of hybrid parallel execution, B and C classes of BT-MZ in NPB version 3.3 were used. And the parallel scalability test has finished with Tachyon's 1024 processes. It is the first time in Korea to get a result of hybrid parallel computing calculation using more than 1024 processes. Hybrid parallel method in high performance computing system with multi-core technology like Tachyon describes that it can be very efficient and useful parallel performance benchmarks.

• KIPS Transactions on Computer and Communication Systems
• /
• v.7 no.3
• /
• pp.67-72
• /
• 2018

Recently, noise reduction in an axial fan producing the small pressure rise and large flow rate, which is one type of turbomachine, is recognized as essential. This study describes the design and optimization techniques of MPI parallel program to simulate the flow-induced noise in the axial fan. In order to simulate the code using 100 million number of grids for flow and 70,000 points for noise sources, we parallelize it using the 2D domain decomposition. However, when it is involved many computing cores, it is getting slower because of MPI communication overhead among nodes, especially for the noise simulation. Thus, it is adopted the one-sided communication to reduce the overhead of MPI communication. Moreover, the allocated memory and communication between cores are optimized, thereby improving 2.97x compared to the original one. Finally, it is achieved 12x and 6x faster using 6,144 and 128 computing cores of KISTI Tachyon2 than using 256 and 16 computing cores for the flow and noise simulations, respectively.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.11a
• /
• pp.163-166
• /
• 2002

복잡한 계산 화학 문제의 해결과 신물질 개발을 위한 나노물질 계산 등을 위해서는 고성능 컴퓨팅 파워가 필요하다. 그러나 이러한 계산을 위해 필요한 실험 장비의 가격은 천문학적으로 증가하고 있어 문제 해결의 장애물로 인식되고 있다. 그런데 최근 '그리드(Grid) 컴퓨팅'이라는 새로운 컴퓨팅이 제안되면서 지리적으로 떨어진 여러 자원들을 하나의 슈퍼컴퓨터처럼 사용할 수 있게 되었다. 그러나 그리드 환경을 이용하려면 그리드 미들웨어인 글로버스(globus)를 설치하고 인증기관을 통해 사용자 인증과 호스트인증을 거친 후 응용 프로그램들을 설치하여 수행하여야 한다. 이러한 복잡한 과정을 거쳐야 그리드 환경의 응용프로그램을 실행 할 수 있고, 실행할 수 있더라도 그리드 환경에서 작업을 요청하고 할당하려면 RSL이라는 스크립트 언어를 사용해야하는 번거로운 작업이 필요하다. 따라서 본 논문에서는 복잡한 화학계산과 나노물질 계산을 위한 응용프로그램들을 인터넷 상에서 쉽게 수행할 수 있도록 그리드 환경을 구축하고 웹 인터페이스를 구현한다.

• Proceedings of the Korea Contents Association Conference
• /
• 2007.11a
• /
• pp.221-225
• /
• 2007

PC grid computing is a paradigm of distributed computing that are collection the idle resource of numerous PCs to perform large-scale. As this way, created high performance resources use a large-scale computational application, also this paradigm studied new measurement in place of application using super computer. This paper suggests ORRS(Open Resource Registration System) that selects a adequate resource what application client want. This system register descriptions of resource that provide group, such as organization, party, team, PCs idle resource in open archive. Also, this system provide PC grid computing environment which is select suitable resource actively what application client want.

• The Journal of the Korea Contents Association
• /
• v.17 no.7
• /
• pp.93-100
• /
• 2017

Recently, demands for high-performance flash-based storage devices (i.e., flash SSD) have rapidly grown in social network services, cloud computing, super-computing, and enterprise storage systems. The industry and academic communities made the NVMe specification for high-performance storage devices, and NVMe-based flash SSDs can be now obtained in the market. In this article, we evaluate performance of NoSQL databases that social network services and cloud computing services heavily adopt by using NVMe-based flash SSDs. To this end, we use NVMe SSD that Samsung Electronics recently developed, and the SSD used in this study has performance up to 3.5GB/s for sequential read/write operations. We use WiredTiger for NoSQL databases, and it is a default storage engine for MongoDB. Our experimental results show that log processing in NoSQL databases is a major overhead when high-performance NVMe-based flash SSDs are used. Furthermore, we optimize components of log processing and optimized WiredTiger show up to 15 times better performance than original WiredTiger.

• Journal of the Korean Society of Industry Convergence
• /
• v.26 no.1
• /
• pp.1-14
• /
• 2023

To secure national future competitiveness, the Korean government announced the 『National Ultra-High Performance Computing (HPC) Innovation Strategy (2021.5.28.)』 and set three innovation strategy goals throughout establishing an innovation ecosystem. This study presented a heterogenous data-based strategic support framework that allowed to understand both the current status of domestic & foreign R&D areas and domestic industrial economy areas in terms of strategic fields related to ultra-high performance computing, and the empirical research was conducted in the life science and public health area. The HPC innovation ecosystem platform based on the connection of heterogeneous data (domestic R&D project-technology-industry-overseas R&D project) presented in this study provided useful and essential information that allowed establishing a specific action plan for the national HPC innovation strategy and contributing to vitalizing the innovation ecosystem. Since the evidence-based policy assumes that a more reasonable consensus is reached through a non-biased decision- making process among stakeholders, the proposed platform may contribute to enhancing policy momentum by increasing legitimacy and trust of planning of the national HPC strategy.

• Journal of the Korean Data and Information Science Society
• /
• v.10 no.2
• /
• pp.473-483
• /
• 1999

We introduce a way to construct a supercomputing capable system with some networked PCs, running the Linux operating system and computing power comparable with expensive commercial workstations, and with the Parallel Virtual Machine (PVM) software which enables one to control the total CPUs and memories of the networked PCs. By benchmarking the system using a PVM parallel program, we find that the system's parallel efficiency is close to 90 %.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.04a
• /
• pp.71-72
• /
• 2017

PLSI 통합 슈퍼컴퓨팅 서비스 환경에서는 다수의 사이트에서 클러스터 시스템 간 데이터 공유를 위해 글로벌 파일시스템을 사용하고 있으나, 수백 노드 이상의 클라이언트와 파일 서버 간 통신이 이루어지는 병렬 I/O에서 네트워크 병목 현상 이 발생할 수 있다. 따라서, 본 연구에서는 네트워크 병목 현상이 PLSI 글로벌 파일 시스템의 I/O 성능에 미치는 영향을 분석한다. PLSI 글로벌 파일시스템 테스트 베드에서 실험을 통해 네트워크 스위치의 버퍼 크기가 병목 현상을 유발하며, 네트워크 스위치의 버퍼 용량을 증가하여 I/O 성능을 개선할 수 있음을 보여준다.