• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.31 no.4
• /
• pp.16-25
• /
• 2003

A parallel computing environment based on Windows operating system was constructed and a performance test was mode in comparison with Linux based systems. The Windows 2000 cluster was composed with servers and clients connected by Fast-ethernet, within which two sub-clusters may operates together or separately. Compaq Visual Fortran complier and two MPI libraries, MPICH.NT.1.2.2 and NT-MPICHNT.1.2 were installed as computing tools. Parallel computing performance tests were carried out using two-dimensional preconditioned Navier-Stokes code to examine the dependency on the number of processors, problem size and MPI libraries, those were compared with results from Linux clusters. Results shows that a cluster based on the user-friendly Windows operating system is also useful for the parallel computing and has good performance comparable to the previous Linux clusters.

• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.1_2
• /
• pp.35-43
• /
• 2006

An MPI Checkpointer is a tool which provides fault-tolerance through checkpointing The previous researches related to the MPI checkpointer have focused on automatic checkpointing and recovery capabilities, but they haven't considered portability issues. In this paper, we discuss design and implementation issues considered for portability when we developed an MPI checkpointer called STFT. In order to increase portability, firstly STFT supports the abstraction interface for a single process checkpointer. Secondly, STFT uses a user-based checkpointing method, and limits possible checkpointing places a user can make. Thirdly, STFT lets the MPI_Init create network connections to the other MPI processes in a fixed order. With these features, we expect STFT can be easily adaptable to various platforms and MPI implementations, and confirmed STFT is easily adaptable to LAM and MPICH/P4 with the prototype Implementation.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.2
• /
• pp.221-233
• /
• 2008

In general, we use a Parallel processing computer manufactured specially for the purpose of parallel processing to do high performance computings. But we can depoly and use a PC cluster composed of several common PCs instead of the very expensive parallel processing computer. A common way to get a PC cluster is to adopt the star topology network connected by a switch hub. But in this paper, we grope efficient implementations of hypercube networks based on TCP/IP to connect 8 PCs directly for more useful parallel processing environment, and make evaluations on functionality and efficiency of them using ping, netperf, MPICH. The two proposed methods of implementation are IP configuration based on link and IP configuration based on node. The results of comparison between them show that there is not obvious difference in performance but the latter is more efficient in simplicity of routing table. For verification of functionality, we compare the parallel processing results of an application in them with the same in a star network based PC cluster. These results also show that the proposed hypercube networks support a perfect parallel processing environment respectively.

• Journal of KIISE:Computing Practices and Letters
• /
• v.11 no.4
• /
• pp.293-304
• /
• 2005

In this paper, we research on job migration in a grid computing environment with cactus and MPICH-C2 based on Globus. Our concepts are to perform job migration by finding the site with plenty of computational resources that would decrease execution time in a grid computing environment. The Migration Manager recovers the job from the checkpointing files and restarts the job on the migrated site. To select a migrating site, the proposed method considers system's performance index, cpu's load, network traffic to send migration job tiles and the execution time predicted on a migration site. Then it selects a site with maximal performance gains. By selecting a site with minimum migration time and minimum execution time. this approach implements a more efficient grid computing environment. The proposed method Is proved by effectively decreasing total execution time at the $K\ast{Grid}$.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.05a
• /
• pp.245-248
• /
• 2008

최근 RFID 시스템의 채택이 다양한 분야에서 빠르게 진행되고 있다. 그러나 RFID 시스템의 대중화를 위해서는 RFID 태그의 정보를 무단으로 획득함으로써 발생할 수 있는 프라이버시 침해 문제를 해결해야 한다. 이 문제를 해결하기 위해서 기존 연구들 중에서 가장 안전한 M. Ohkubo 등의 Hash-Chain 기법이 있다. 그러나 이 기법은 태그를 판별할 때 엄청난 태그 수의 증가로 인해 막대한 계산 능력을 요구하는 문제점이 있다. 따라서 본 논문에서는 프라이버시 보호를 유지하면서 태그판별시간 절감을 위해서 그리드 환경으로의 이식과 노드별로 m/k개의 SP를 분할하는 균등분할 알고리즘을 적용한 태그 판별 처리 모델을 제안한다. 제안 모델을 그리드 환경에서 동시에 수행할 수 있다면 이상적인 경우 태그를 판별하는 시간은 1/k로 감소한다.

• 한국전산유체공학회:학술대회논문집
• /
• 2001.10a
• /
• pp.58-62
• /
• 2001

Aparallel computing environment was constructed based on Windows 2000 operating system. This cluster was configured using Fast-Ethernet system to hold up together the clients within a network domain. For the parallel computation, MPI implements for Windows such as MPICH.NT.1.2.2 and MP-MPICHNT.1.2 were used with Compaq Visual Fortran compiler which produce a well optimized executives for x86 systems. The evaluation of this cluster performance was carried out using a preconditioned Navier-Stokes code for the 2D analysis of a compressible and viscous flow around a compressor blade. The parallel performance was examined in comparison with those of Linux clusters studied previously by changing a number of processors, problem size and MPI libraries. The result from the test problems presents that parallel performance of the low cost Fast-Ethernet Windows cluster is superior to that of a Linux cluster of similar configuration and is comparable to that of a Myrinet cluster.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2005.05a
• /
• pp.929-932
• /
• 2005

D-클래스의 계산은 NP-완전 문제로서 그 결과를 개인키, 공개키로 이용하여 보안에 응용될 수 있는 가능성을 가지고 있으나 계산 복잡도로 인해 현재 극히 제한된 크기의 행렬에 대한 D-클래스만이 알려져 있다. 이 문제를 해결하기 위해 D-클래스 계산을 효율적으로 할 수 있는 수식과 알고리즘을 설계 및 구현하였지만, 행렬의 크기가 증가함에 따라 결과를 얻는 것에는 한계가 있다. 이것을 해결하기 위해 많은 컴퓨터를 사용할 수 있는 그리드 컴퓨팅이 필요하다. 본 논문은 그리드 컴퓨팅 환경에서 최적화된 알고리즘 설계 및 구현을 위해 Globus 가 설치된 클러스터를 구축하고, MPICH 를 이용 효율적인 D-클래스의 계산 알고리즘을 설계 및 구현하여 실행 결과에 대해 논한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.04a
• /
• pp.389-392
• /
• 2002

광선 추적 기법은 컴퓨터를 활용하여 사진과 같은 고해상도의 영상을 얻어내기 위한 렌더링 기법 중 하나이다. 그러나 이 기법은 이미지를 생성할 때 각 접마다 시뮬레이션을 하여 계산해 내므로 접의 수에 따른 계산량이 증가되고 그에 따른 계산 시간이 많이 소요된다는 단점이 있다. 이러한 많은 계산량을 처리하기 위해 병렬처리 기법을 활용할 수 있다. 본 논문에서는 MPI(Message Passing Interface)를 이용한 병렬 광선 추적 기법을 제시하고 그러한 기법을 여러대의 PC를 이용한 PC Clustering 기법에 적용시켜봄으로써 복잡한 계산에 소요되는 시간을 단축시키고자 하였다. 또한 작업의 크기의 변화에 따른 작업 시간과 노드 수의 증가에 따른 속도 향상률을 알아보았다. 이러한 실험을 위해 병렬 프로그래밍 도구로는 Windows NT 기반의 MPICH를 사용하였고 노드의 수는 3대에서 30대까지 증가시켰다. 노드의 수가 증가함에 따라 렌더링에 소요되는 시간이 선형적으로 감소함을 알 수 있었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.05a
• /
• pp.121-124
• /
• 2003

계산량이 매우 큰 작업의 경우는 단일 프로세서를 이용할 경우 많은 계산 시간이 소요된다 이러한 문제점을 극복하고자 저비용 고효율의 PC Clustering 기법을 사용하면 비용적인 절감의 효과를 얻을 수 있다. 본 논문은 PC Clustering을 이용한 병렬처리를 수행함으로써 시간의 단축을 도모하되 표준 MPI 함수 중 Collective Communication을 취급하는 함수들의 성능을 향상시켜 개선하고 그 성능을 측정하는데 목적이 있다. 또한 표준 MPI 함수를 사용하는 MPICH와 표준 MPI 함수 중 Collective Communication을 사용하는 함수들의 데이터를 압축하여 전송하도록 MPI를 개선하였다. 실험은 윈도우 2000을 탑재한 20개의 노드를 가지는 시스템을 이용하였다. 본 실험의 견과로써 데이터의 양과 노드 수를 증가시킬수록 압축 MPI의 성능이 표준 MPI의 성능을 능가함을 확인할 수 있었다.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.1
• /
• pp.1-7
• /
• 2019

In this paper, we implemented a Wi-Fi based cluster system using raspberry pi for multidisciplinary education. The cluster implementation on the desktop was more difficult to maintain the complexity, big size, high price, power consumption as the number of nodes increased. In this paper, we implemented a cluster using Raspberry Pi, which is developed for educational purposes, to reduce the cost of connecting nodes. In addition, the complexity of system construction is reduced by replacing the connection between each node with Wi-Fi. Also, the inconvenience of configuration due to node increase was reduced. It is expected that the implementation of the cluster will be a good alternative in the educational environment where distributed processing and parallel processing are performed in the embedded environment. Also, it is confirmed that it can be applied to the multidisciplinary education.