• 인터넷정보학회논문지
• /
• 제6권1호
• /
• pp.65-72
• /
• 2005

플래시 메모리는 이동형 컴퓨팅 환경에서 휴대용 정보기기를 지원하는 우수한 미디어이다. 플래시 메모리는 비휘발성, 낮은 전력소모, 빠른 데이터 접근 속도 등의 특징으로 휴대용 정보기기용 데이터베이스의 핵심 저장 모듈이 되었다. 하지만, 일반 RAM 메모리에 비하여 상대적으로 느린 연산 특성을 고려하여 기존의 트랜잭션 처리 기법을 개선할 필요가 있다. 이를 위하여, 본 논문은 플래시인지 트랜잭션 관리(Flash-Aware Transaction Management: FATM) 기법을 제안한다. FATM은 SRAM과 W-cache를 활용하여 트랜잭션 처리 성능을 높인다. 또한, 성능 검증을 위하여 시뮬레이션 모델을 제안하였으며, 실험 결과 분석을 통하여 FATM이 기존의 트랜잭션 처리 기법보다 우수함을 확인하였다.

• Smart Structures and Systems
• /
• 제18권4호
• /
• pp.663-682
• /
• 2016

Continuum manipulators as a kind of mechanical arms are useful tools in special robotic applications. In medical applications, like colonoscopy, a maneuverable thin and flexible manipulator is required. This research is focused on developing a basic module for such an application using shape memory alloys (SMA). In the structure of the module three wires of SMA are uniformly distributed and attached to the circumference of a flexible tube. By activating wires, individually or together, different rotation regimes are provided. SMA model is used based on Brinson work. The SMA model is combined to model of flexible tube to provide a composite model of the module. Simulating the model in Matlab provided a platform to be used to develop controller. Complex and nonlinear behavior of SMA make the control problem hard especially when a few SMA actuators are active simultaneously. In this paper, position control of the two degree of freedom module is under focus. An experimental control strategy is developed to regulate a desired position in the module. The simulation results present a reasonable performance of the controller. Moreover, the results are verified through experiments and show that the continuum module of this paper would be used in real modular manipulators.

• 한국전산유체공학회지
• /
• 제19권2호
• /
• pp.24-29
• /
• 2014

In this study, a parallel performance of CUPID-code has been investigated for both Ethernet and Infiniband network system to examine the effect of cache memory and network-speed. Bi-conjugate gradient solver of CUPID-code has been parallelised by using domain decomposition method and message passing interface (MPI). It is shown that the parallel performance of Ethernet-network system is worse than that of Infiniband-network system due to the slow network-speed and a small cache memory. It is also found that the parallel performance of each system deteriorates for a small problem due to the communication overhead, but the performance of Infiniband-network system is better than Ethernet-network system due to a much faster network-speed. For a large problem, the parallel performance depends less on network system.

• 정보처리학회논문지:컴퓨터 및 통신 시스템
• /
• 제8권10호
• /
• pp.245-250
• /
• 2019

모바일 분야의 발전으로 인해 낸드 플래시 메모리의 사용이 급증하였다. 그러나 낸드 플래시 메모리는 수명에 제한이 있어서 수명을 예측하기 위한 연구가 진행되고 있다. 낸드 플래시 메모리의 수명에 큰 영향을 주는 요소 중 하나가 워크로드인데, 모바일 환경에서의 워크로드 분석 연구는 미비하다. 이에 본 논문에서는 안드로이드 기반의 스마트폰을 사용하면서 발생하는 트레이스를 수집하고, 모바일 환경에서의 워크로드 분포를 분석하였다. 수집한 트레이스는 hotness 그룹을 3개로 분류할 수 있다. 또한 트레이스의 분포는 무거운 꼬리를 가지는 형태이다. 본 논문은 이를 Pareto, Lognormal, Weibull 분포에 피팅하였고, 그 결과 Pareto 분포에 가장 가까운 것을 확인하였다.

• 대한금속재료학회지
• /
• 제47권12호
• /
• pp.787-796
• /
• 2009

The fracture toughness improvement of Ni-Mn-Ga-Fe ferromagnetic shape memory alloys containing ductile particles was explained by direct observation of microfracture processes using an in situ loading stage installed inside a scanning electron microscope (SEM) chamber. The Ni-Mn-Ga-Fe alloys contained a considerable amount of ductile particles in the grains after the homogenization treatment at $800{\sim}1100^{\circ}C$. ${\gamma}$ particles were coarsened and distributed homogeneously along {$\beta}$ grain boundaries as well as inside {$\beta}$ grains as the homogenization temperature increased. The in situ microfracture observation results indicated that ${\gamma}$ particles effectively acted as blocking sites of crack propagation, and provided stable crack growth that could be confirmed by the R-curve analysis. This increase in fracture resistance with increasing crack length improved overall fracture properties of the alloys containing ${\gamma}$ particles.

• 한국정보통신학회논문지
• /
• 제10권8호
• /
• pp.1414-1421
• /
• 2006

본 논문에서는 VOD에서 스트리밍 데이터를 효율적으로 서비스할 수 있는 Consistency 알고리즘을 제시한다. 미디어 데이터 서비스를 위해 우선 하나의 미디어 데이터를 라운드 로빈 방식으로 스트라이핑하여 각 호스트의 저장 노드에 저장한다. 본 논문에서는 일반적인 계산 용도로 사용되는 barrier 메커니즘을 미디어 플레이 최소 단위인 (SH, GOP) 미디어 데이터에 서비스할 수 있도록 제시하였다. 데이타 처리 방식은 하나의 호스트에 한 프래그먼트 크기의 공유메모리를 할당한다. 이 공유메모리 는 barrier 메커니즘을 통하여 RTP패킷 전송 단위로 결정될 프래그먼트 데이터의 조합을 형성한다. 본 논문에서 제시한 알고리즘에 대해서 실험을 수행하기 위해서 VOD 시스템에서 프로그램을 작성하였다.

• 한국전산유체공학회:학술대회논문집
• /
• 한국전산유체공학회 2005년도 추계 학술대회논문집
• /
• pp.157-162
• /
• 2005

Parallel implementation and performance assessment of the grid assembly in a structured chimera grid approach is studied. The grid assembly process, involving hole cutting and searching donor, is parallelized on the PC cluster. A message passing programming model based on the MPI library is implemented using the single program multiple data(SPMD) paradigm. The coarse-grained communication is optimized with the minimized memory allocation because that the parallel grid assembly can access the decomposed geometry data in other processors by only message passing in the distributed memory system such as a PC cluster. The grid assembly workload is based on the static load balancing tied to flow solver. A goal of this work is a development of parallelized grid assembly that is suited for handling multiple moving body problems with large grid size.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.334-337
• /
• 2005

This paper describes the implementation of DCS communication network that provides high bandwidth and reliability. The network for DCS in this paper adopts the Reflective Memory (RM) architecture and Fast Ethernet physical media that have 100Mbps bandwidth. Also, this network uses Ring Enhancement Device (RED) which was invented to reduce the time delay of each node. The DCS network that is introduced in this paper is named as ERCNet(Ethernet based Real-time Control Network). This paper describes the architecture and working algorithms of ERCNet and performs numerical analysis. In addition, the performance of ERCNet is evaluated by experiment using the developed ERCNet network.

• 전자통신동향분석
• /
• 제13권5호통권53호
• /
• pp.11-22
• /
• 1998

Recently, scalable multiprocessor systems are actively developed for general-purpose computing, which are based on distributed shared memory (DSM) architecture to boost up both programmability and scalability. In this paper, we survey and analyze cache coherence protocols in non-uniform memory access (NUMA) multiprocessor systems. In particular, it has been easily inferred that specialized hardware suitable for NUMA multiprocessor systems with commodity symmetric multiprocessors (SMPs) is highly required. The cache coherence protocol combined with specialized hardware can significantly improve the performance and scalability of NUMA multiprocessor systems, providing better programmability.

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 2001년도 봄 학술발표회 논문집
• /
• pp.61-68
• /
• 2001

A parallel nonlinear analysis program of prestressed concrete frame is migrated on a PC cluster system and a massively parallel processing system, CRAY T3E system, using MPI. The PC cluster system is configured with Pentium Ⅲ class PCs and fast ethernet. The CRAY T3E system is composed of a set of nodes each containing one Processing Element (PE), a memory subsystem and its distributed memory interconnect network. Parallel computing algorithms are implemented on element-wise processing parts including the calculation of stiffness matrix, element stresses and determination of material states, check of material failure and calculation of unbalanced loads. Parallel performance of the migrated program is evaluated through typical numerical examples.