• Journal of Mechanical Science and Technology
• /
• v.18 no.5
• /
• pp.814-819
• /
• 2004

The conceptual design of a rotorcraft system involves many different analysis disciplines. The decomposition of such a system into several subsystems can make analysis and design more efficient in terms of the total computation time. Adaptive parallel decomposition makes the structure of the overall design problem suitable to apply the multidisciplinary design optimization methodologies and it can exploit parallel computing. This study proposes a decomposition method which adaptively determines the number and sequence of analyses in each sub-problem corresponding to the available number of processors in parallel. A rotorcraft design problem is solved and as a result, the adaptive parallel decomposition method shows better performance than other previous methods for the selected design problem.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.24 no.2
• /
• pp.161-197
• /
• 2020

Total variation minimization is standard in mathematical imaging and there have been numerous researches over the last decades. In order to process large-scale images in real-time, it is essential to design parallel algorithms that utilize distributed memory computers efficiently. The aim of this paper is to illustrate recent advances of domain decomposition methods for total variation minimization as parallel algorithms. Domain decomposition methods are suitable for parallel computation since they solve a large-scale problem by dividing it into smaller problems and treating them in parallel, and they already have been widely used in structural mechanics. Differently from problems arising in structural mechanics, energy functionals of total variation minimization problems are in general nonlinear, nonsmooth, and nonseparable. Hence, designing efficient domain decomposition methods for total variation minimization is a quite challenging issue. We describe various existing approaches on domain decomposition methods for total variation minimization in a unified view. We address how the direction of research on the subject has changed over the past few years, and suggest several interesting topics for further research.

• 한국전산유체공학회:학술대회논문집
• /
• 1998.11a
• /
• pp.147-152
• /
• 1998

2-D flow fields are studied by using a shared memory parallel computer with a parallel flow analysis program which uses domain decomposition method and MPI library for data exchange at overlapped interface. Especially, effects of directional domain decomposition on parallel efficiency are studied for 2-D Lid-Driven cavity flow and flow through square cavity. It is known from the present study that domain decomposition along the main flow direction gives better parallel efficiency in 1-D partitioning than along the other direction. 2-D partitioning, however, is less sensitive to flow directions and gives good parallel efficiency for most of the cases considered.

• Communications of the Korean Mathematical Society
• /
• v.10 no.3
• /
• pp.735-750
• /
• 1995

We present a domain decomposition algorithm for solving large sparse linear systems of equations arising from queuing networks. Such techniques are attractive since the problems in subdomains can be solved independently by parallel processors. Many of the methods proposed so far use some form of the preconditioned conjugate gradient method to deal with one large interface problem between subdomains. However, in this paper, we propose a "nested" domain decomposition method where the subsystems governing the interfaces are small enough so that they are easily solvable by direct methods on machines with many parallel processors. Convergence of the algorithms is also shown.lso shown.

• Proceedings of the KSME Conference
• /
• 2000.11a
• /
• pp.818-823
• /
• 2000

In practical design studies, most of designers solve multidisciplinary problems with complex design structure. These multidisciplinary problems have hundreds of analysis and thousands of variables. The sequence of process to solve these problems affects the speed of total design cycle. Thus it is very important for designer to reorder original design processes to minimize total cost and time. This is accomplished by decomposing large multidisciplinary problem into several multidisciplinary analysis subsystem (MDASS) and processing it in parallel. This paper proposes new strategy for parallel decomposition of multidisciplinary problem to raise design efficiency by using genetic algorithm and shows the relationship between decomposition and multidisciplinary design optimization (MDO) methodology.

• Journal of computational fluids engineering
• /
• v.3 no.1
• /
• pp.22-29
• /
• 1998

Parallel implementation is conducted for a SIMPLER finite volume model. The present parallelism is based on domain decomposition and explicit message passing using MPI and SHMEM. Two parallel solvers to tridiagonal matrix equation are employed. The implementation is verified on the Cray T3E system for a benchmark problem of natural convection in a sidewall-heated cavity. The test results illustrate good scalability of the present parallel models. Performance issues are elaborated in view of convergence as well as conventional parallel overheads and single processor performance. The effectiveness of a localized matrix solution algorithm is demonstrated.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.10
• /
• pp.90-97
• /
• 1996

This paper presents an efficient parallel implementation and its performance evaluations of a SOFM neural netowrk on the multicomputer. We investigate the parallel performance as the size of a neural network N, the number of the patterns L, and the number of the processors p increase. We propose an analytica performance evaluation model for eac of the parallel implementations and verified the validity of the model through experiments. Analytical result show that the number of processors for a maximum speedup of the network decomposition nd the training-set decomposition increases in proportion to .root.N and .root.L, respectively. The performances of the both decompositions depend on the number of training patterns L and the size of the neural network N and, if L.geq.0.423N, the performance of trhe training-set decomposition is proved to be better than that of the network decomposition.

• Journal of Internet Computing and Services
• /
• v.14 no.6
• /
• pp.41-47
• /
• 2013

GP-GPUs are general purposed GPUs for numerical computation based on multiple threads which are originally for graphic processing. GP-GPUs provide cache memory in a form of shared memory which user programs can access directly, unlikely typical cache memory. In this research, we implemented the parallel block LU decomposition program to utilize cache memory in GP-GPUs. The parallel blocked LU decomposition program designed with Nvidia CUDA C run 7~8 times faster than nun-blocked LU decomposition program in the same GP-GPU computation environment.

• Journal of Mechanical Science and Technology
• /
• v.19 no.11
• /
• pp.2007-2015
• /
• 2005

A large-scale analysis to evaluate complex material and structural behaviors is one of interesting topic in diverse engineering and scientific fields. Also, the utilization of massively parallel processors has been a recent trend of high performance computing. The objective of this paper is to introduce a parallel process system which consists of general purpose finite element analysis solver as well as parallelized PC cluster. The later was constructed using eight processing elements and the former was developed adopting both hierarchical domain decomposition method and balancing domain decomposition method. Then, to verify the efficiency of the established system, it was applied for structural analysis of steam generator in nuclear power plant. Since the prototypal evaluation results agreed well to the corresponding reference solutions it is believed that, after reinforcement of PC cluster by increasing number of processing elements, the promising parallel process system can be utilized as a useful tool for advanced structural integrity evaluation.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.22 no.1
• /
• pp.35-44
• /
• 2009

This paper describes an application of domain decomposition method for parallel finite element analysis which is required to large scale 3D structural analysis. A parallel finite element method system which adopts a domain decomposition method is developed. Node is generated if its distance from existing node points is similar to the node spacing function at the point. The node spacing function is well controlled by the fuzzy knowledge processing. The Delaunay triangulation method is introduced as a basic tool for element generation. Domain decomposition method using automatic mesh generation system holds great benefits for 3D analyses. Aa parallel numerical algorithm for the finite element analyses, domain decomposition method was combined with an iterative solver, i.e. the conjugate gradient(CG) method where a whole analysis domain is fictitiously divided into a number of subdomains without overlapping. Practical performance of the present system are demonstrated through several examples.