2014, Vol.19, No.9

Journal of The Korea Society of Computer and Information 2023 KCI Impact Factor : 0.65

pISSN : 1598-849X / eISSN : 2383-9945
https://journal.kci.go.kr/jksci

In this paper, we propose MPI gridding algorithm of LiDAR data that minimizes thecommunication between the cores. The LiDAR data collected from aircraft is a 3D spatialinformation which is used in various applications. Since there are many cases where the LiDAR data has too high resolution than actually required or non-surface information is included in thedata, filtering the raw LiDAR data is required. In order to use the filtered data, the interpolationusing the data structure to search adjacent locations is conducted to reconstruct the data. Sincethe processing time of LiDAR data is directly proportional to the size of it, there have been manystudies on the high performance parallel processing system using MPI. However, previouslyproposed methods in parallel approach possess possible performance degradations such asimbalanced data size among cores or communication overhead for resolving boundary conditioninconsistency. We conduct empirical experiments to verify the effectiveness of our proposedalgorithm. The results show that the total execution time of the proposed method decreased up to4.2 times than that of the conventional method on heterogeneous clusters.

In this paper, we propose a real-time video transcoding scheme for N-Screen service based oncloud computing. This scheme creates an intro-block and several playback blocks by splitting theoriginal video. And there is the first service request, after transmitting the intro-block, transmitsthe playback blocks that converting the blocks on real-time. In order to completing trans-codingwithin playback time of each block, we split and allocate the block to node according toperformance of each node. Also, in order to provide real-time video playback service, the previous scheme convert original video into all format and resolution. However we show that the proposedscheme can reduce storage usage by converting original video into format with proper resolutionsuitable to device and platform of client. Through simulation, we show that it is more effective toreal-time video playback for N-screen service than the previous method. We also show that theproposed scheme uses less storage usage than previous method.

Singular value decomposition (SVD) has been widely used to identify unique features from adata set in various fields. However, a complex matrix calculation of SVD requires tremendouscomputation time. This paper improves the performance of a representative one-sided block Jacobyalgorithm using a two-dimensional (2D) multi-core system. In addition, this paper explores anoptimal multi-core system by varying the number of processing elements in the 2D multi-coresystem with the same 400MHz clock frequency and TSMC 28nm technology for each matrix-basedone-sided block Jacoby algorithm (128x128, 64x64, 32x32, 16x16). Moreover, this paper demonstrates the potential of the 2D multi-core system for the one-sided block Jacoby algorithmby comparing the performance of the multi-core system with a commercial high-performancegraphics processing unit (GPU).