• Journal of computational fluids engineering
• /
• v.19 no.2
• /
• 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.

• Journal of Institute of Control, Robotics and Systems
• /
• v.6 no.6
• /
• pp.492-499
• /
• 2000

In this paper, realization techniques of the parallel processing and the parallel network system for image processing are described. The parallel image processing system is constructed by the characterization of image processing and processor. Several problems are solved to achieve effective parallel processing and processor networking with the particular properties of image processing, which are reduction of communication quantity, equalization of load and delay depreciation on communication. A parallel image input device is developed for the flexible networking of parallel image processing. An abnormal region detection algorithm which is the basic function in machine vision is applied to evaluate the constructed parallel image processing system. The performance and effectiveness of the system are confirmed by experiments.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.30B no.5
• /
• pp.120-128
• /
• 1993

In this paper, an implementation of high-speed parallel processing system for neural network design on the multicomputer network is presented. Linear speedup expandability is increased by reducing the synchronization penalty and the communication overhead. Also, we presented the parallel processing models and their performance evaluation models for each of the parallization methods of the neural network. The results of the experiments for the character recognition of the neural network bases on the proposed system show that the proposed approach has the higher linear speedup expandability than the other systems. The proposed parallel processing models and the performance evaluation models could be used effectively for the design and the performance estimation of the neural network on the multicomputer network.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2000.11a
• /
• pp.224-228
• /
• 2000

In this paper, the kinematics of the new type of parallel manipulator is studied, and neural network is applied to solve the forward kinematics problem. The parallel manipulator, called a Stewart platform, has an easy and unique solution about the inverse kinematics, however the forward kinematics is difficult to get the solution because of the lack of an efficient algorithm due to its highly nonlinearity. This paper proposes the neural network scheme as an alternative Newton-Raphson method. The neural network is found to improve its accuracy by adjusting the offset of the result obtained.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.1 no.1
• /
• pp.35-53
• /
• 1997

This paper analyzes the time complexity of Genetic Algorithm based Task Scheduling (GATS) which is designed for the scheduling of parallel programs with diverse embedded parallelism types in a heterogeneous network systems. The analysis of time complexity is performed based on two representation methods (REIA, REIS) which are proposed in this paper to encode the scheduling information. And the heterogeneous network systems consist of a set of loosely coupled parallel and vector machines connected via a high-speed network. The objective of heterogeneous network computing is to solve computationally intensive problems that have several types of parallelism, on a suite of high performance and parallel machines in a manner that best utilizes the capabilities of each machine. Therefore, when scheduling in heterogeneous network systems, the matching of the parallelism characteristics between tasks and parallel machines should be carefully handled in order to obtain more speedup. This paper shows how the parallelism type matching affects the time complexity of GATS.

• Communications for Statistical Applications and Methods
• /
• v.19 no.3
• /
• pp.459-469
• /
• 2012

This article proposes a couple of parallel implementations of the self-organizing network for normal mixtures. In principle, self-organizing networks should be able to be implemented in a parallel computing environment without issue. However, the network for normal mixtures has inherent problem in being operated parallel in pure sense due to estimating conditional expectations of the mixing proportion in each iteration. This article shows the result of the parallel implementations of the network using Java. According to the results, both of the implementations achieved a faster execution without any performance degradation.

• The KIPS Transactions:PartB
• /
• v.13B no.6 s.109
• /
• pp.615-624
• /
• 2006

The objective of this paper is to implement parallel multi-layer ANN(Artificial Neural Network) simulator based on the mobile agent system which is executed in parallel in the virtual parallel distributed computing environment. The Multi-Layer Neural Network is classified by training session, training data layer, node, md weight in the parallelization-level. In this study, We have developed and evaluated the simulator with which it is feasible to parallel the ANN in the training session and training data parallelization because these have relatively few network traffic. In this results, we have verified that the performance of parallelization is high about 3.3 times in the training session and training data. The great significance of this paper is that the performance of ANN's execution on virtual parallel computer is similar to that of ANN's execution on existing super-computer. Therefore, we think that the virtual parallel computer can be considerably helpful in developing the neural network because it decreases the training time which needs extra-time.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.17 no.3
• /
• pp.1-7
• /
• 2008

This paper describes the kinematics which is a new type of parallel manipulator, and the neural network is applied to solving the forward kinematics problem. The parallel manipulator called it as a Stewart platform has an easy and unique solution about the inverse kinematics. However, the forward kinematics is difficult to get a solution because of the lack of an efficient algorithm caused by its highly nonlinearity. This paper proposes the neural network scheme of an Newton-Raphson method alternatively. It is found that the neural network can be improved its accuracy by adjusting the offset of the obtained result.

• 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 the Korean Institute of Telematics and Electronics C
• /
• v.34C no.6
• /
• pp.44-50
• /
• 1997

This paper describes the design and test of an on-line non-invasive network performance monitor (hardware portion) for the SPAX parallel computer. The SPAX parallel computer supports up to 256 intel P6 processors with 4 P6 processors constituting a processign node. The nodes are interconnected with a dual two-level crossbar network calle dXcent-net. Since the performance of the SPAX parallel computer is highly dependent on the proper and efficient operation of the network, an on-line non-invasive network performance monitor (with hardware components) has been developed to aid in the monitoring and tunign of the Xcent-net. Successful testing of a prototype node monitor board and PC interface system shows that our monitor design provides a low-cost practical solution to this problem.