• The KIPS Transactions:PartA
• /
• v.13A no.6 s.103
• /
• pp.533-540
• /
• 2006

This paper describes the design and implementation of a grid system META (Metacomputing Environment using Test-run of Application) which facilitates the execution of a CFD (Computational Fluid Dynamics) analysis program on distributed environment. The grid system META allows the CFD program developers can access the computing resources distributed over the network just like one computer system. The research issues involved in the grid computing include fault-tolerance, computing resource selection, and user-interface design. In this paper, we exploits an automatic resource selection scheme for executing the parallel SPMD (Single Program Multiple Data) application written in MPI (Message Passing Interface). The proposed resource selection scheme is informed from the network latency time and the elapsed time of the kernel loop attained from test-run. The network latency time highly influences the executional performance when a parallel program is distributed and executed over several systems. The elapsed time of the kernel loop can be used as an estimator of the whole execution time of the CFD Program due to a common characteristic of CFD programs. The kernel loop consumes over 90% of the whole execution time of a CFD program.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.11
• /
• pp.2835-2844
• /
• 1998

Most data parallel languages provide the block-cyclic distribution (cyclic(k)) that is one of the most general regular distributions. In order to generate local addresses for an array section A(l:h:s) with block-cyclic distribution, efficient compiling methods or run-time methods are required. In this paper, two local address generation methods for the block-cyclic distribution are presented. One is a simple scan method that is modified from the virtual-block scheme. The other is a linear-time ${\Delta}M$ table that contains the local memory access information construction method. This method is simpler than other algorithms for generating a ${\Delta}M$ table. Experimental results show that a simple that a simple scan method has poor performance but a linear-time ${\Delta}M$ table generation method is faster than other algorithms in ${\Delta}M$ table generation time and access time for 10,000 array elements.

• The KIPS Transactions:PartA
• /
• v.16A no.2
• /
• pp.55-60
• /
• 2009

Race conditions in current Java programs must be detected because it may cause unexpected result by non-deterministic executions. For detecting such races during program execution, execution flows of all threads and all access events can be monitored. It is difficult for previous race detection techniques to monitor all threads and access events in actuality because these techniques analyze the files traced during program execution or modify original source programs and then monitor these programs. This paper presents a transparent scalable monitoring tool to detect races using JDI(Java Debug Interface) where JDI is 100% pure java interface to provide in JDPA(Java Platform Debugger Architecture) and is able to provide information corresponding to events occurred in run-time of programs. This tool thus can monitor execution flows of all threads and all access events without program modification. We prove transparency of the presented tool and grasp the efficiency of it using a set of published benchmark programs. As a result of this, the suggested tool can monitor all threads and accesses of these programs without their modification, and their monitoring time is increased to more than 20 times.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.1
• /
• pp.13-21
• /
• 2010

IEEE 1149.1 test architecture was proposed to support the test of elements within the boards. It is a large serial shift register that uses the TDI pin as an input and the TDO pin as an output. Even though it performs the board level test perfectly, there is a problems of running system level test when the boards are equipped to the system. To test real time operation signal on test pin, output speed of serial shift register chain must be above double clock speed of shift register. In this paper, we designed a runtime test architecture and a runtime test procedure under running system environments to capture runtime signal at system clock rate. The suggested runtime test architecture are simulated by Altera Max+Plus 10.0. through the runtime test procedure. The simulation results show that operations of the suggested runtime test architecture are very accurate.

• Journal of Internet Computing and Services
• /
• v.9 no.2
• /
• pp.43-50
• /
• 2008

In IEEE 802.11b wireless LAN, stations keep synchronization by receiving beacons being periodically sent by the AP (access point) when they run in low power mode. Beacon transmission is delayed if wireless channel is busy at a scheduled TBTT (target beacon transmission time), and stations must be awake until they receive the delayed beacon. In this paper, we propose a scheme that stations get their transmission delayed if they have little time for successful data transmission by the next TBTT. Beacon transmission without delay is guaranteed at every TBTT with this method so that the awake time of low power stations to receive beacon can be reduced. The proposed method is simulated and its characteristics ore described with the analysis of the results. The measured results in terms of beacon delay show some enhancement in energy consumption.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.1D
• /
• pp.119-127
• /
• 2008

Nowaday, the local governments eager to change their transport system aiming for public transport oriented one. However, it is more important to change the land use system in the catchment areas of public transport in order to enhance its usage sustainably for the long run. This research aims to seek maximal spatial extent of the catchment areas of the Seoul Metropolitan Subway in consideration of its urban spatial structure in order to accommodate the potential users living around the subway stations. For this task the empirical data of the household travel survey for the Seoul Metropolitan Area conducted 2002 were analysed. It was founded that the walking access times to the subway stations, which can represent their spatial extents, are related to their travel times, but differently according to their given positions in the urban spatial structure. The characteristics of subway commuters also affect them with the conditions. It is to be expected that the results of this research can contribute to an enhancement of its usage by applying to land-use policies of the catchment areas.

• Journal of Magnetics
• /
• v.21 no.4
• /
• pp.491-495
• /
• 2016

We developed an embedded Object-Oriented Micromagnetic Frame (OOMMF) script schemes for more flexible simulations for complex and dynamic mircomagnetic behaviors. The OOMMF can be called from any kind of softwares by system calls, and we can interact with OOMMF by updating the input files for next step from the output files of the previous step of OOMMF. In our scheme, we set initial inputs for OOMMF simulation first, and run OOMMF for ${\Delta}t$ by system calls from any kind of control programs. After executing the OOMMF during ${\Delta}t$, we can obtain magnetization configuration file, and we adjust input parameters, and call OOMMF again for another ${\Delta}t$ running. We showed one example by using scripting embedded OOMMF scheme, tunneling magneto-resistance dependent switching time. We showed the simulation of tunneling magneto-resistance dependent switching process with non-uniform current density using the proposed framework as an example.

• Journal of KIISE:Computer Systems and Theory
• /
• v.29 no.7
• /
• pp.384-393
• /
• 2002

A Parallel file system is normally used to support excessive file requests from parallel applications in a cluster system, whereas prefetching is useful for improving the file system performance. This paper proposes a new prefetching method, Fips(dynamic File Prefetching Scheme based on file access patterms), that is particularly suitable for parallel scientific applications and multimedia web services in a parallel file system. The proposed prefetching method introduces a dynamic prefetching scheme to predict data blocks precisely in run-time although the file access patterns are irregular. In addition, it includes an algorithm to determine whether and when the prefetching is performed using the current available I/O bandwidth. Experimental results confirmed that the use of the proposed prefetching policy in a parallel file system produced a higher file system performance.

• Journal of Advanced Navigation Technology
• /
• v.12 no.2
• /
• pp.154-163
• /
• 2008

In a mobile broadband wireless access (MBWA) network, many users access a base station (BS), which relays data transferred from high-speed wired network to low-speed wireless network. For this difference of their data rate, a BS suffers from the lack of its buffer space when many users run multiple applications at the same time, and thus packet losses occur. TCP, which guarantees end-to-end reliability, is used as transport protocol also in wireless networks. But TCP lowers their transmission rate incorrectly and frequently whenever packet losses occur. And they increase their transmission rate differently with each other; finally TCP throughput of each TCP flow varies largely, and then TCP fairness goes worse. In this paper, a scheme that controls packet transmission rate adaptively according to TCP flows' transmission rate, that prevents buffer overflows at BS, and that guarantees TCP fairness at a certain degree is proposed. As it is analyzed by simulations, the proposed scheme enhances TCP fairness by maintaining TCP throughput of each TCP sender similarly with each other.

• Journal of IKEEE
• /
• v.23 no.1
• /
• pp.91-98
• /
• 2019

LTE's extension for unlicensed spectrum called Licensed Assisted Access (LAA) is equipped with Listen-Before-Talk (LBT) designed similar with the backoff mechanism of Wi-Fi for coexistence. However, Wi-Fi's backoff mechanism has not evolved from its old design for compatibility with legacy devices, thus LAA's LBT is not efficient either in utilizing spectrum. If LAA operates with no Wi-Fi systems in proximity, it can run more efficient LBT. In this paper, we propose Narrowband Clear Channel Assessment (NCCA) for narrowband transmission. In NCCA, an LAA node performs LBT in either wide or each narrow bandwidth segment. This allows multiple LAA nodes to perform simultaneous transmissions in orthogonal bandwidth segments in the same time slot. We design four variants of NCCA implementation and model their performance using a mathematical model. The coexistence performance of NCCA with conventional wideband nodes and the accuracy of the model are shown via simulation.