Go to the main menu
Skip to content
Go to bottom
REFERENCE LINKING PLATFORM OF KOREA S&T JOURNALS
> Journal Vol & Issue
Journal Basic Information
Journal DOI :
Electronics and Telecommunications Research Institute
Editor in Chief :
Volume & Issues
Volume 20, Issue 4 - Dec 1998
Volume 20, Issue 3 - Sep 1998
Volume 20, Issue 2 - Jun 1998
Volume 20, Issue 1 - Mar 1998
Selecting the target year
Evaluation of Cluster-Based System for the OLTP Application
Hahn, Woo-Jong ; Yoon, Suk-Han ; Lee, Kang-Woo ; Dubois, Michel ;
ETRI Journal, volume 20, issue 4, 1998, Pages 301~301
In this paper, we have modeled and evaluated a new parallel processing system called Scalable Parallel computer Architecture based on Xbar (SPAX) for commercial applications. SMP systems are widely used as servers for commercial applications; however, they have very limited scalability. SPAX cost-effectively overcomes the SMP limitation by providing both scalability and application portability. To investigate whether the new architecture satisfies the requirements of commercial applications, we have built a system model and a workload model. The results of the simulation study show that the I/O subsystem becomes the major bottleneck. We found that SPAX can still meet the I/O requirement of the OLTP workload as it supports flexible I/O subsystem. We also investigated what will be the next most important bottleneck in SPAX and how to remove it. We found that the newly developed system network called Xcent-Net will not be a bottleneck in the I/O data path. We also show the optimal configuration that is to be considered for system tuning.
A Repeated Mapping Scheme of Task Modules with Minimum Communication Cost in Hypercube Multicomputers
Kim, Joo-Man ; Lee, Cheol-Hoon ;
ETRI Journal, volume 20, issue 4, 1998, Pages 327~327
This paper deals with the problem of one-to-one mapping of 2
task modules of a parallel program to an n-dimensional hypercube multicomputer so as to minimize the total communication cost during the execution of the task. The problem of finding an optimal mapping has been proven to be NP-complete. First we show that the mapping problem in a hypercube multicomputer can be transformed into the problem of finding a set of maximum cutsets on a given task graph using a graph modification technique. Then we propose a repeated mapping scheme, using an existing graph bipartitioning algorithm, for the effective mapping of task modules onto the processors of a hypercube multicomputer. The repeated mapping scheme is shown to be highly effective on a number of test task graphs; it increasingly outperforms the greedy and recursive mapping algorithms as the number of processors increases. Our repeated mapping scheme is shown to be very effective for regular graphs, such as hypercube-isomorphic or 'almost' isomorphic graphs and meshes; it finds optimal mappings on almost all the regular task graphs considered.
An Asynchronous Algorithm for Balancing Unpredictable Workload on Distributed-Memory Machines
Chung, Yong-Hwa ; Park, Jin-Won ; Yoon, Suk-Han ;
ETRI Journal, volume 20, issue 4, 1998, Pages 346~346
It is challenging to parallelize problems with irregular computation and communication. In this paper, we propose an asynchronous algorithm for balancing unpredictable workload on distributed-memory machines. By using an initial workload estimate, we first partition the computations such that the workload is distributed evenly across the processors. In addition, we perform task migrations dynamically for adapting to the evolving workload. To demonstrate the usefulness of our load balancing strategy, we conducted experiments on an IBM SP2 and a Cray T3D. Experimental results show that our task migration strategy can balance unpredictable workload with little overhead. Our code using C and MPI is portable onto other distributed-memory machines.
Improved Multi-band Transfer Matrix Method for Calculating Eigenvalues and Eigenfunctions of Quantum Well and Superlattice Structures
Kim, Byoung-Whi ; Jun, Yong-Il ; Jung, Hee-Bum ;
ETRI Journal, volume 20, issue 4, 1998, Pages 361~361
We present an improved transfer matrix algorithm which can be used in solving general n-band effective-mass
equation for quantum well structures with arbitrary shaped potential profiles(where n specifies the number of bands explicitly included in the effective-mass equation). In the proposed algorithm, specific formulas are presented for the three-band (the conduction band and the two heavy- and light-hole bands) and two-band (the heavy- and light-hole bands) effective-mass eigensystems. Advantages of the present method can be taken in its simple and unified treatment for general
matrix envelope-function equations, which requires relatively smaller computation efforts as compared with existing methods of similar kind. As an illustration of application of the method, numerical computations are performed for a single GaAs/AlGaAs quantum well using both the two-band and three-band formulas. The results are compared with those obtained by the conventional variational procedure to assess the validity of the method.
Temperature Distribution of a Low Temperature Heat Pipe with Multiple Heaters for Electronic Cooling
Noh, Hong-Koo ; Song, Kyu-Sub ;
ETRI Journal, volume 20, issue 4, 1998, Pages 380~380
A numerical study has been performed to predict the characteristics on the transient operation of the heat pipe with multiple heaters for electronic cooling. The model of the heat pipe was composed of the evaporator section with four heaters, insulated transport section, and the condensor section with a conductor which is cooled with uniform heat flux condition to surrounding. The governing equations and the boundary conditions were solved by the generalized PHOENICS computational code employing the finite volume method. Two test cases are investigated in present study; Case 1 indicates that the 1st and 2nd heaters among four heating sources are heated off, while the 3rd and 4th heaters are heated on. Case 2 is the inverse situation switched from heating location of Case 1. The results show that the transient time to reach the steady state is shorter for Case 1 than for Case 2. Especially, the temperature difference of the heater during switching operation is relatively small compared to the maximum allowable operating temperature difference in electronic system. Hence, it is predicted that the heat pipe in present study operates with thermally good reliability even for switching the heaters.