• 한국전산유체공학회:학술대회논문집
• /
• 2006.05a
• /
• pp.94-99
• /
• 2006

As part of a Department of Defense Grand Challenge Project, advanced high performance computing (HPC) time-accurate computational fluid dynamics (CFD) techniques have been developed and applied to a new area of aerodynamic research on microjets for control of small and medium caliber projectiles. This paper describes a computational study undertaken to determine the aerodynamic effect of flow control in the afterbody regions of spin-stabilyzed projectiles at subsonic and low transonic speeds using an advanced scalable unstructured flow solver in various parallel computers such as the IBM SP4 and Linux Cluster. High efficiency is achieved for both steady and time-accurate unsteady flow field simulations using advanced scalable Navier-Stokes computational techniques. Results relating to the code's portability and its performance on the Linux clusters are also addressed. Numerical simulations with the unsteady microjets show the jets to substantially alter the flow field both near the jet and the base region of the projectile that in turn affects the forces and moments even at zero degree angle of attack. The results have shown the potential of HPC CFD simulations on parallel machines to provide to provide insight into the jet interaction flow fields leading to improve designs.

• The KIPS Transactions:PartA
• /
• v.8A no.4
• /
• pp.299-310
• /
• 2001

In this paper, we study the methodology of distributing the requests of clients based on the state of real server in the LVS(Linux virtual server) clustering system. The WLC(weighted least connection) algorithm in the LVS cluster system is studied. The load distributing algorithm which assigns a weight into each real server is devised by considering the load of real servers. The load test is executed to estimate the load of real servers using a load generating tool. Throughout the result of the experiment, we suggest new load distributing algorithm based on the usage of physical memory of each real server. It is shown that the correction potentiality of new algorithm is somewhat better than that of the WLC algorithm.

• Journal of KIISE:Computer Systems and Theory
• /
• v.34 no.9
• /
• pp.407-415
• /
• 2007

In parallel cluster computing systems, the efficiency of communication between computing nodes is one of important factors that decide overall system performance. Accordingly, many researchers have studied on high-performance inter-node communication. The recently launched multi-core processor, however. increases the importance of intra-node communication as well because the more the number of cores in a node, the more the number of parallel processes running in the same node. Though there have been studies on intra-node communications, these have limited considerations on the state-of-the-art systems. In this paper, we propose a Linux kernel module that minimizes the number of data copy by exploiting the memory mapping mechanism for high-performance intra-node communication. The proposed kernel module supports the Linux kernel version 2.6. The performance measurements over a multi-core system present that the proposed kernel module can achieve lower latency up to 62% and higher throughput up to 144% than an existing kernel module approach. In addition, the measurements reveal that the performance of intra-node communication can vary significantly based on whether the cores that run the communication processes are belong to the same processor package (i.e., sharing the L2 cache).

• Journal of the Korean earth science society
• /
• v.43 no.1
• /
• pp.60-76
• /
• 2022

This study presents a software full setup and the following test execution times in a Linux cluster for the United Kingdom Earth System Model (UKESM) and then compares the model results from control and experimental simulations of the UKESM relative to various observations. Despite its low resolution, the latest version of the UKESM can simulate tropospheric chemistry-aerosol processes and the stratospheric ozone chemistry using the United Kingdom Chemistry and Aerosol (UKCA) module. The UKESM with UKCA (UKESM-UKCA) can treat atmospheric chemistryaerosol-cloud-radiation interactions throughout the whole atmosphere. In addition to the control UKESM run with the default CMIP5 SO₂ emission dataset, an experimental run was conducted to evaluate the aerosol effects on meteorology by changing atmospheric SO₂ loading with the newest REAS data over East Asia. The simulation period of the two model runs was 28 years, from January 1, 1982 to December 31, 2009. Spatial distributions of monthly mean aerosol optical depth, 2-m temperature, and precipitation intensity from model simulations and observations over East Asia were compared. The spatial patterns of surface temperature and precipitation from the two model simulations were generally in reasonable agreement with the observations. The simulated ozone concentration and total column ozone also agreed reasonably with the ERA5 reanalyzed one. Comparisons of spatial patterns and linear trends led to the conclusion that the model simulation with the newest SO₂ emission dataset over East Asia showed better temporal changes in temperature and precipitation over the western Pacific and inland China. Our results are in line with previous finding that SO₂ emissions over East Asia are an important factor for the atmospheric environment and climate change. This study confirms that the UKESM can be installed and operated in a Linux cluster-computing environment. Thus, researchers in various fields would have better access to the UKESM, which can handle the carbon cycle and atmospheric environment on Earth with interactions between the atmosphere, ocean, sea ice, and land.

• Journal of the Korean earth science society
• /
• v.43 no.6
• /
• pp.691-711
• /
• 2022

The state-of-the-art Earth system model as a virtual Earth is required for studies of current and future climate change or climate crises. This complex numerical model can account for almost all human activities and natural phenomena affecting the atmosphere of Earth. The Unified Model (UM) from the United Kingdom Meteorological Office (UK Met Office) is among the best Earth system models as a scientific tool for studying the atmosphere. However, owing to the expansive numerical integration cost and substantial output size required to maintain the UM, individual research groups have had to rely only on supercomputers. The limitations of computer resources, especially the computer environment being blocked from outside network connections, reduce the efficiency and effectiveness of conducting research using the model, as well as improving the component codes. Therefore, this study has presented detailed guidance for installing a new version of the UM on high-performance parallel computers (Linux clusters) owned by individual researchers, which would help researchers to easily work with the UM. The numerical integration performance of the UM on Linux clusters was also evaluated for two different model resolutions, namely N96L85 (1.875° ×1.25° with 85 vertical levels up to 85 km) and N48L70 (3.75° ×2.5° with 70 vertical levels up to 80 km). The one-month integration times using 256 cores for the AMIP and CMIP simulations of N96L85 resolution were 169 and 205 min, respectively. The one-month integration time for an N48L70 AMIP run using 252 cores was 33 min. Simulated results on 2-m surface temperature and precipitation intensity were compared with ERA5 re-analysis data. The spatial distributions of the simulated results were qualitatively compared to those of ERA5 in terms of spatial distribution, despite the quantitative differences caused by different resolutions and atmosphere-ocean coupling. In conclusion, this study has confirmed that UM can be successfully installed and used in high-performance Linux clusters.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.12
• /
• pp.2885-2890
• /
• 2014

Localization of a sensor network node using machine learning has been recently studied. It is easy for Support vector machines algorithm to implement in high level language enabling parallelism. Raspberrypi is a linux system which can be used as a sensor node. Pi can be used to construct IP based Hadoop clusters. In this paper, we realized Support vector machine using python language and built a sensor network cluster with 5 Pi's. We also established a Hadoop software framework to employ MapReduce mechanism. In our experiment, we implemented the test sensor network with a variety of parameters and examined based on proficiency, resource evaluation, and processing time. The experimentation showed that with more execution power and memory volume, Pi could be appropriate for a member node of the cluster, accomplishing precise classification for sensor localization using machine learning.

• Proceedings of the IEEK Conference
• /
• 2003.07d
• /
• pp.1633-1636
• /
• 2003

In this paper, we developed the scheme to grow to use newly added disk space without having to kill the application, unmount file system. This scheme, called online resizing, can resize the file system layout with the advent of Logical Volume Manager. The online resizing scheme is designed and implemented in linux cluster system where multiple hosts share the disk data in storage area network environment. It is incorporated with SANfs shared file system and can perform resizing technique with SANfs-VM volume manager. The experimental result shows that it can maximize the availability and capacity of the SANfs system which are important for modem servers where must not lose their customer.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2003.11a
• /
• pp.461-465
• /
• 2003

클러스터 파일 시스템은 데이터 입출력 대역폭을 극대화하여 효율성을 높이고 각 노드의 입출력 부담을 균등하게 부과하기 위하여 원본 파일을 여러 노드에 분산 저장한다. 이렇게 파일을 노드들에 분산 저장하기 위해서는 효율적인 노드간 데이터 통신을 필요로 하며, 노드 내부에서도 클러스터 파일 시스템과 어플리케이션과의 효율적인 전용 데이터 교환 메커니즘을 지원해야 한다. 이를 위해 사용자 수준 통신 프로토콜인 VIA를 선정하여 운영체제(Operating System)의 간섭으로 인한 네트워크 계층간의 데이터 복사에 의한 병목현상을 줄이고자 하였다. 본 논문에서는 노드간 데이터 통신을 위해 M-VIA를 이용하여 통신모듈을 설계 및 구현하였다. 그리고 실제 성능테스트를 통하여 기존의 소켓 기반인 TCP/IP를 이용한 통신모듈과의 성능을 비교 평가하고 확인 한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07a
• /
• pp.52-54
• /
• 2005

Beowulf 타입의 리눅스 클러스터 시스템의 핵심노드인 계산노드는 일반적으로 범용 엔트리급 서버 및 PC 등을 이용하여 구성되며, 이 계산노드의 성능은 전체 클러스터의 계산 성능을 결정하는 가장 중요한 요소 중의 하나이다. 이에 본 논문에서는 현재 시중에서 유통 중인 대표적인 로엔드 플랫폼-Xeon, P-IV, Opteron, Athlon64-들을 대상으로 HPL, NPB, stream등 고성능 컴퓨팅 분야에서 널리 쓰이는 벤치마킹 테스트 도구를 사용하여 개별 노드의 성능을 측정하여 비교 분석하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.11a
• /
• pp.127-130
• /
• 2003

웹 클러스터 시스템은 인터넷에서 요청되는 부하를 여러 실제 서버들에게 분산시켜서 어플리케이션에 따른 처리와 응답을 하는 서버 단 시스템이다. 부하는 서비스를 제공하는 서비스에 따라 다른 성향을 띄게 되므로 서비스 제공자는 부하의 특성을 파악하여 알맞은 웹 클러스터 시스템을 사용하여야 효율적이고 좋은 성능을 보이게 된다. 이 논문에서는 7 개의 다른 성향의 부하 상황과 Alteon Web Switch, ALBM Traffic Manager와 Linux Virtual Server를 사용하여 클러스터를 구성하고 각 부하 상황에서 클러스터 시스템들이 어떤 성능을 보여주는지 비교 분석한다.