• 한국항공우주학회지
• /
• 제31권10호
• /
• pp.1-9
• /
• 2003

컴퓨팅 그리드 환경에서는 컴퓨팅 그리드 시스템을 구성하는 단위 시스템들의 성능이 균일하지 않기 때문에, 영역을 균등하게 분할하는 일반적인 로드밸런싱 기법을 적용하기가 적절하지 않다. 본 연구에서는 그래프 분할기법을 기반으로 하여, 컴퓨팅 그리드 시스템을 구성하는 단위 시스템들의 성능가중치를 계산하여 분할하는 2단계 영역 분할 기법을 제시하였다. 2단계 영역 분할 기법 시 발생하는 통신량의 증가는 그래프 분할기법인 WEVM을 적용하여 최소화 할 수 있었으며, 멀티 클러스터 환경과 WAN에서 타당성과 효율성을 검증해 보았다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권11호
• /
• pp.5491-5505
• /
• 2017

Use of the Gaussian inverse Wishart PHD (GIW-PHD) filter has demonstrated promise as an approach to track an unknown number of extended targets. However, the partitioning approaches used in the GIW-PHD filter, such as distance partition with sub-partition (DP-SP), prediction partition (PP) and expectation maximization partition (EMP), fails to provided accurate partition results when targets are spaced closely together and performing maneuvers. In order to improve the performance of a GIW-PHD filter, this paper presents a cooperation partitioning (CP) algorithm to solve the partitioning issue when targets are spaced closely together. In the GIW-PHD filter, the DP-SP is insensitive to target maneuvers but sensitive to the differences in target sizes, while EMP is the opposite. The proposed CP algorithm is a fusion approach of DP-SP and EMP, which employs EMP as a sub-partition approach after DP. Therefore, the CP algorithm will be sensitive to neither target maneuvers nor differences in target sizes. The simulation results show that the use of the proposed CP algorithm will improve the performance of the GIW-PHD filter when targets are spaced closely together.

• 한국게임학회 논문지
• /
• 제13권4호
• /
• pp.25-34
• /
• 2013

3D 게임에서 충돌 탐지를 효과적으로 하기 위해 구성하는 공간 분할 트리는 분할 평면을 결정하는데 트리 밸런스와 분할 평면과 겹치는 폴리곤의 개수 등을 고려해야 한다. 본 논문에서는 3D 게임 공간 분할 트리에서 트리 빌드 조건에 대한 가중치를 제어하는 휴리스틱 알고리즘을 제안하였다. 가중치의 변화에 따라서 트리 빌드 시간, 분할 평면과 겹치는 폴리곤을 쪼갤 때 시각적 불일치를 유발할 수 있는 T-junction 의 제거 시간, 트리 밸런스에 따른 렌더링 속도(frame per second) 등을 3D 게임 시뮬레이션을 통하여 분석하였다.

• ETRI Journal
• /
• 제37권3호
• /
• pp.562-572
• /
• 2015

For a multiprocessor System-on-Chip (MPSoC) to achieve high performance via parallelism, we must consider how to partition a given application into different components and map the components onto multiple processors. In this paper, we propose a software pipeline-based partitioning method with cyclic dependent task management and communication optimization. During task partitioning, simultaneously considering computation load balance and communication optimization can cause interference, which leads to performance loss. To address this issue, we formulate their constraints and apply an integer linear programming approach to find an optimal partitioning result - one that requires a trade-off between these two factors. Experimental results on a reconfigurable MPSoC platform demonstrate the effectiveness of the proposed method, with 20% to 40% performance improvements compared to a traditional software pipeline-based partitioning method.

• 한국정보처리학회논문지
• /
• 제4권11호
• /
• pp.2891-2902
• /
• 1997

본 논문은 실시간 시스템에서 주기 및 비주기적 태스크들의 마감시간 만족을 위한 캐쉬(캐쉬 메모리)의 최적 분할 형태를 분석한다. 연구 목적은 태스크들의 가용비용을 최소화하여 태스크들의 마감시간 위반율을 줄일 뿐 아니라 캐쉬의 유휴공간을 다른 태스크에게 할당시키기 위함이다. 이를 위해 캐쉬의 분할공간에 태스크들을 할당시키기 위한 캐쉬 분할공간 할당 알고리즘을 제시한다. 여기에서 태스크들이 할당된 캐쉬 분할공간들의 집합을 캐쉬 분할 형태라고 한다. 태스크들이 분할공간에 어떻게 할당되는가에 따라 다양한 캐쉬 분할 형태들을 얻을 수 있다. 이러한 캐쉬 분할 형태들로부터 스케쥴링 가능한 태스크들의 가용비용의 한계범위와 태스크들이 최소 가용비용으로 실행 할 수 있는 캐쉬의 최 적 분할 형태를 분석한다．

• 한국콘텐츠학회논문지
• /
• 제21권7호
• /
• pp.164-170
• /
• 2021

VLSI 설계에서의 분할(partitioning)은 기능의 최적화를 위하여 설계하고자 하는 회로의 그룹화(grouping)하는 단계로서 레이아웃(layout)에서 면적과 전파지연의 최소화를 위해 함께 배치할 소자를 결정하는 문제이다. 이러한 분할 문제에서 해를 얻기 위해 사용되는 알고리즘은 Kernighan-Lin 알고리즘, Fiduccia Mattheyses heuristic, 시뮬레이티드 어닐링, 유전자 알고리즘 등의 방식이 이용된다. 본 논문에서는 회로 분할 문제에 대하여 유전자 알고리즘과 확률 진화 알고리즘을 결합한 어댑티드 유전자 알고리즘을 이용한 해 공간 탐색(solution space search) 방식을 제안하였으며, 제안한 방식을 유전자 알고리즘 및 시뮬레이티드 어닐링 방식과 비교, 분석하였고, 어댑티드 유전자 알고리즘이 시뮬레이티드 어닐링 및 유전자 알고리즘보다 더 효과적으로 최적해에 근접하는 것을 알 수 있었다.

• Journal of Microbiology and Biotechnology
• /
• 제2권2호
• /
• pp.135-140
• /
• 1992

The partitioning of recombinant human interleukin-2(rhII-2) in PEG 8000-dextran 38800 aqueous two-phase system has been investigated using three different sources of rhIL-2. In the case of pure rhIL-2, the solubility in a PEG-dextran two-phase system was low and most of rhIL-2 was partitioned into the bottom phase. For the recovery of rhIL-2 from insoluble protein aggregates, the inclusion bodies of recombinant E. coli were solubilized by the treatment with sodium dodecyl sulfate (SDS). The addition of SDS significantly enhanced not only the solubility of rhIL-2 but also the partitioning of rhIL-2 to the top phase. When the ratio of SDS to rhIL-2 was 2.0, the partition coefficient(K) and the recovery yield(Y) at the top phase were 4.5 and 88%, respectively, at pH 6.8. In order to reduce the recovery steps further, SDS was directly added to the intact recombinant E. coli cells and then partitioned into the PEG/dextran aqueous two-phase system. The observed partition coefficient ($K{\cong{3.0$) and recovery yield ($Y{\geq}80%$ )of this method were comparable to the rhIL-2 recovery from insoluble protein aggregates. The results obtained in this work indicate that PEG-dextran two-phase partitioning might provide a simple way for the recovery and partial purification of recombinant proteins which are produced as inclusion bodies.

• 방사성폐기물학회지
• /
• 제21권3호
• /
• pp.397-410
• /
• 2023

This study examined the efficacy of various chlorinating agents in partitioning light water reactor spent fuel, with the aim of optimizing the chlorination process. Through thermodynamic equilibrium calculations, we assessed the outcomes of employing MgCl₂, NH₄Cl, and Cl₂ as chlorinating agents. A comparison was drawn between using a single agent and a sequential approach involving all three agents (MgCl₂, NH₄Cl, and Cl₂). Following heat treatment, the utilization of MgCl₂ as the sole chlorinating agent resulted in a moderate separation. Specifically, this method yielded a solid separation with 96.9% mass retention, 31.7% radioactivity, and 44.2% decay heat, relative to the initial spent fuel. In contrast, the sequential application of the chlorinating agents following heat treatment led to a final solid separation characterized by 93.1% mass retention, 5.1% radioactivity, and 15.4% decay heat, relative to the original spent fuel. The findings underscore the potential effectiveness of a sequential chlorination strategy for partitioning spent fuel. This approach holds promise as a standalone technique or as a complementary process alongside other partitioning processes such as pyroprocessing. Overall, our findings contribute to the advancement of spent fuel management strategies.

• 한국경영과학회지
• /
• 제19권3호
• /
• pp.219-233
• /
• 1994

A fixed k-coloring problem is introduced and dealt with by efficient heuristic algorithms. It is shown that the problem can be transformed into the graph partitioning problem. Initial coloring and improving methods are proposed for problems with and with and without the size restriction. Algorithm Move, LEE and OEE are developed by modifying the Kernighan-Lin's two way uniform partitioning procedure. The use of global information in the selection of the node and the color set made the proposed algorithms superior to the existing method. The computational result also shows that the superiority does not sacrifice the time demand of the proposed algorithms.

• International Journal of Contents
• /
• 제1권1호
• /
• pp.40-44
• /
• 2005

This paper introduces region partitioning method of non-perfect nested loops with non-uniform dependences. This kind of loop normally can't be parallelized by existing parallelizing compilers and transformations. Even when parallelized in rare instances, the performance is very poor. Based on the Convex Hull theory which has adequate information to handle non-uniform dependences, this paper proposes an enhanced region partitioning method which divides the iteration space into minimum parallel regions where all the iterations inside each parallel region can be executed in parallel by using variable renaming after copying.