Hyoungwoo Park

GAIS: grid advanced information service based on P2P mechanism

In this paper, we propose an information service component of Moredream which we refer to as GAIS, for providing advanced functionalities and more plentiful resource information in order to satisfy the requirements for the various applications in the K/sup */Grid computing environment characterized by both high performance and high throughput computing. In particular, GAIS includes interfaces and functionalities for the dynamic VO management, universal VO discovery, service categorization and efficient information providers. Consequently, we anticipate that our Grid information service be broadly utilized through the improved service qualities.

A Model of Problem Solving Environment for Integrated Bioinformatics Solution on Grid by Using Condor

To solve the real-world bioinformatics problems on grid, the integration of various analysis tools is necessary in addition to the implementation of basic tools. Workflow based problem solving environment on grid can be the efficient solution for this type of software development. Here we propose a model of simple problem solving environment that enables component based workflow design of integrated bioinformatics applications on Grid environment by using Condor functionalities.

MPICH-GP: a Private-IP-Enabled MPI over grid environments

This paper presents an overview of MPICH-GP, which extends the MPICH-G2 functionality to support private IP clusters. To support the communication among private IP clusters, the MPICH-GP uses a communication relay scheme combining the NAT and a user-level proxy. The benchmarking results show that MPICH-GP outperforms the user-level two-proxy scheme used in PACX-MPI and Firewall-enabled MPICH-G, and also show comparable application performance to that of original MPICH-G2, especially in large message (or problem) size.

The cost of checkpointing, logging and recovery for the mobile agent systems

The reliable execution of a mobile agent is a very important design issue to build a mobile agent system and many fault-tolerant schemes have been proposed. Hence, we present the experimental evaluation of the performance of the fault-tolerant schemes for the mobile agent environment. Our evaluation focuses on the checkpointing schemes and deals with the cooperating agents.

An efficient collective communication method for grid scale networks

This research is to design a collection of effective collective operations for the Grid scale network environment. In the Grid, several network features should be specified and adapted into the algorithmic design of collective operations. For this, we characterize the Grid and design hierarchical latency optimal tree algorithm for the MPI (message passing interface) library. The experimental results show that performance gain in performing collective operations can be achieved by around 160% compared with MPICH-G2 which is based on the flat algorithm.

Dynamic Topology Selection for High Performance MPI in the Grid Environments

MPI (Message Passing Interface) is getting more popular and important even in the Grid, but its performance still remains a problem, which is caused by the communication bottleneck on wide area links. To overcome such performance wall problem, we propose a dynamic topology selection which provides an effective resource selection service based on the principles of wide area message passing. It attempts to match the communication pattern of application with the topology of resources. Consequently, the proposed method provides an optimized set of resources and improves overall application performance by reducing the communication delay. To demonstrate the proposed method, we executed parallel benchmark programs and measured each execution time in five geometrically distributed clusters by changing resource selection method. When using topology selection method, experimental results show that performance gain can be achieved by up to 200%.

Design and Implementation of Dynamic Process Management for Grid-Enabled MPICH

This paper presents the design and impementation of MPI_Rejoin() for MPICH-GF, a grid-enabled fault tolerant MPICH implementation. To provide fault tolerance to the MPI applications, it is mandatory for a failed process to recover and continue execution. However, current MPI implementations do not support dynamic process management and it is not possible to restore the information regarding communication channels. The ‘rejoin’ operation allows the restored process to rejoin the existing group by updating the corresponding entries of the channel table with the new physical address. We have verified that our implementation can correctly reconstruct the MPI communication structure by running NPB applications. We also report on the cost of ‘rejoin’ operation.

An NAT-Based Communication Relay Scheme for Private-IP-Enabled MPI over Grid Environments

In this paper we propose a communication relay scheme combining the NAT and a user-level proxy to support private IP clusters in Grid environments. Compared with the user-level two-proxy scheme used in PACX-MPI and Firewall-enabled MPICH-G, the proposed scheme shows performance improvement in terms of latency and bandwidth between the nodes located in two private IP clusters. Since the proposed scheme is portable and provides high performance, it can be easily applied to any private IP enabled solutions including the private IP enabled MPICH solution for Globus toolkit.

Toward a grid-based simulation of multiphase fluid flow in porous media

Summary form only given. Modeling fluid flow in a porous medium is a challenging computational problem. It involves closely coupled systems of flow transport process consisted of highly heterogeneous distributions of porous medium property, various fluid flow characteristics including injection or production well assemblies, and surface separation and storage facilities. For the design of better flow management scheme, high performance computing tools have been applied as a useful and essential technique in a cost-effective manner. In recent years, grid computing architectures have been emerging as a new computing environment. It allows a powerful computing capability for accurate simulation of complex fluid flow phenomena that occur in porous media. In this paper, grid-enabled simulation approach is presented for modeling a three dimensional, multiphase fluid flow in the grid computing environment Extensive test results of the code are presented in this paper. The preliminary result shows a significant parallel performance. Based on this preliminary study, we further discuss a future plan for the design of multipurpose porous media flow simulator, which allows multiphysical simulation capability in grid computing environment.

Design and Implementation of a Dynamic Communication MPI Library for the Grid

Abstract The authors design and implement a dynamic and effective communication MPI (Message-Passing Interface) library for the grid environment, especially to design collective operations such as broadcast and reduce. The purpose of the grid environment is to aggregate a large number of resources. So, it is inevitable that networks will be heterogeneous, and thus application performance will be affected. However, these issues have not until now been considered in designing communication primitives. Thus, these characteristics from the grid networks are specified and adapted into the communication algorithm design in this research. For an effective solution, we characterize the grid network on the basis of actual measurement, and design an effective communication algorithm called HLOT (Hierarchical Latency Optimal Tree) that can reduce the communication delay by utilizing the network status aggressively. Also, by using the proposed algorithm, we implement various collective communication routines of MPI library and demonstrate their effectiveness. The experimental results show that performance gain of more than 200% can be achieved in performing collective operations and around 130% in performing an applications benchmark, compared to MPICH-G2, that is, conventional grid-enabled MPI library.