• Journal of information and communication convergence engineering
• /
• v.1 no.4
• /
• pp.169-173
• /
• 2003

The performance of modern mainframe computers keeps increasing due to the advances in the semiconductor technology. However, the quest for the faster computer has never been satisfied. To overcome the discrepancy in the supply and demand, we studied a high performance computer architecture utilizing a three-dimensional Holographic Data Storage Systems (HDSS) as a secondary storage system. The HDSS can achieve a high storage density by utilizing the third dimension. Furthermore, the HDSS can exploit the parallelism by processing the two-dimensional data in a single step. To compare the performance of the HDSS with the conventional hard disk based storage system, we modeled the HDSS using the DiskSim simulation engine and performed the simulation study. Results showed that the HDSS can improve the access time by 1.7 times.

• International Journal of Contents
• /
• v.1 no.1
• /
• pp.50-58
• /
• 2005

Generally, multidimensional data such as image and spatial data require large amount of storage space. There is a limit to store and manage those large amounts of data in single workstation. If we manage the data on parallel computing environment which is being actively researched these days, we can get highly improved performance. In this paper, we propose a parallel multidimensional index structure that exploits the parallelism of the parallel computing environment. The proposed index structure is nP(processor)-nxmD(disk) architecture which is the hybrid type of nP-nD and 1P-nD. Its node structure in-creases fan-out and reduces the height of an index. Also, a range search algorithm that maximizes I/O parallelism is devised, and it is applied to k-nearest neighbor queries. Through various experiments, it is shown that the proposed method outperforms other parallel index structures.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.9
• /
• pp.2827-2835
• /
• 2000

In recent years, much attention has been focused on improving I/O devices' processing speed which is essential in such large data processing areas as multimedia data processing. And studies on high-performance parallel file systems are considered to be one of such efforts. In this paper, an efficient disk allocation scheme is proposed for high-performance parallel file systems. In other words, the concept of a parallel disk file's parallelism is defined using data declustering characteristic of a given parallel file. With the concept, an efficient disk allocation scheme is proposed which calculates the appropriate degree of data declustering on disks for each parallel file in order to obtain the maximum throughput when more than one parallel file is used at the same time. Since, calculation for obtaining the maximum throughput is too complex as the number of parallel files increases, an approximate disk allocation algorithm is also proposed in this paper. The approximate algorithm is very simple and especially provides very good results when I/O workload is high. In addition, it has shown that the approximate algorithm provides the optimal disk allocation for the maximum throughput when the arrival rate of I/O requests is infinite.

• Journal of KIISE:Computer Systems and Theory
• /
• v.34 no.2
• /
• pp.49-56
• /
• 2007

MEMS-based storage is being developed as a new storage media. Due to its attractive features such as high-bandwidth, low-power consumption, high-density, and low cost, MEMS storage is anticipated to be used for a wide range of applications from storage for small handhold devices to high capacity mass storage servers. However, MEMS storage has vastly different physical characteristics compared to a traditional disk. First, MEMS storage has thousands of heads that can be activated simultaneously. Second, the media of MEMS storage is a square structure which is different from the platter structure of disks. This paper presents a new request scheduling algorithm for MEMS storage that makes use of the aforementioned characteristics. This new algorithm considers the parallelism of MEMS storage as well as the seek time of requests on the two dimensional square structure. We then extend this algorithm to consider the aging factor so that starvation resistance is improved. Simulation studies show that the proposed algorithms improve the performance of MEMS storage by up to 39.2% in terms of the average response time and 62.4% in terms of starvation resistance compared to the widely acknowledged SPTF (Shortest Positioning Time First) algorithm.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.2
• /
• pp.497-506
• /
• 2000

RAID systems have been used as a mass storage system with high parallelism and availability. Especially RAID systems with parity declustering are widely studied as a technique to provide high fault tolerancy and availability by reducing performance degradation in case of disk fuilures. In this paper, a new organization of parity declustering with distributed spare units is proposed. And in normal mode where there are no failures, it is shown that these organization can improve the performance of RAID systems. By simulation methods, it is proved that the performance of RAID system in normal mode is improved by 5 to 15%.

• Journal of KIISE:Computer Systems and Theory
• /
• v.26 no.1
• /
• pp.98-106
• /
• 1999

본 논문에서는 대용량 입출력을 수행하는 태스크의 QoS를 제어하기 위한 방법으로사용자가 시스템에 입출력 요구시 요구 대역폭을 제시하고, 파일시스템에서 디스크개소와 입출력 이벤트를 고려하여 입출력의 병렬성을 제어함으로써 QoS를 제어하는 방법을 제안하였다. 그리고, 시스템에서 각 태스크가 주어진 병렬성을 가지고 입출력을 진행하고 있을 때, 요구 대역폭을 가지고 입출력을 요구하는 태스크의 대역폭을 만족시키기 위한 병렬성을 계산하는 분석 모델을 유도하였다. 그리고, 디스크 입출력의 병렬성을 이용하여 대용량 입출력의 QoS를 효율적으로 제어할 수 있음을 분석 모델의 결과를 통해 검증하였다.

• Journal of KIISE:Databases
• /
• v.29 no.1
• /
• pp.58-71
• /
• 2002

Generally, multi-dimensional data such as image and spatial data require large amount of storage space. There is a limit to store and manage those large amount of data in single workstation. If we manage the data on parallel computing environment which is being actively researched these days, we can get highly improved performance. In this paper, we propose a parallel high-dimensional index structure that exploits the parallelism of the parallel computing environment. The proposed index structure is nP(processor)-n$\times$mD(disk) architecture which is the hybrid type of nP-nD and lP-nD. Its node structure increases fan-out and reduces the height of a index tree. Also, A range search algorithm that maximizes I/O parallelism is devised, and it is applied to K-nearest neighbor queries. Through various experiments, it is shown that the proposed method outperforms other parallel index structures.

• Journal of KIISE:Software and Applications
• /
• v.30 no.1_2
• /
• pp.129-139
• /
• 2003

The PC cluster architecture is considered as a cost-effective alternative to the existing supercomputers for realizing a high-performance information retrieval (IR) system. To implement an efficient IR system on a PC cluster, it is essential to achieve maximum parallelism by having the data appropriately distributed to the local hard disks of the PCs in such a way that the disk I/O and the subsequent computation are distributed as evenly as possible to all the PCs. If the terms in the inverted index file can be classified to closely related clusters, the parallelism can be maximized by distributing them to the PCs in an interleaved manner. One of the goals of this research is the development of methods for automatically clustering the terms based on the likelihood of the terms' co-occurrence in the same query. Also, in this paper, we propose a method for duplicate distribution of inverted index records among the PCs to achieve fault-tolerance as well as dynamic load balancing. Experiments with a large corpus revealed the efficiency and effectiveness of our method.

• Journal of KIISE:Databases
• /
• v.32 no.2
• /
• pp.142-150
• /
• 2005

A shared disks (SD) cluster couples multiple computing nodes, and every node shares a common database at the disk level. A great deal of research indicates that the SD cluster is suitable to high performance transaction processing, but the aggregation of SD cluster with real-time processing has not been investigated at all. A real-time transaction has not only ACID properties of traditional transactions but also time constraints. By adopting cluster technology, the real-time services will be highly available and can exploit inter-node parallelism. In this paper, we first develop an experiment model of an SD-based real-time database system (SD-RTDBS). Then we investigate the feasibility of real-time transaction processing in the SD cluster using the experiment model. We also evaluate the cross effect of real-time transaction processing algorithms and SD cluster algorithms under a wide variety of database workloads.

• Journal of Korea Multimedia Society
• /
• v.23 no.2
• /
• pp.241-246
• /
• 2020

Hadoop is a framework to process large data sets in a distributed way across clusters of nodes. It has been a popular platform to process big data, but in recent years, other platforms became competitive ones depending on the characteristics of the application. Spark is one of distributed platforms to enable real-time data processing and improve overall processing performance over Hadoop by introducing in-memory processing instead of disk I/O. Whereas Hadoop is designed to work on Java and data analysis is processed using Java API, Spark provides a variety of APIs with Scala, Python, Java and R. In this paper, the goal is to find out whether the APIs of different programming languages af ect the performances in Spark. We chose two popular APIs: Python and Scala. Python is easy to learn and is used in AI domain in a wide range. Scala is a programming language with advantages of parallelism. Our experiment shows much faster processing with Scala API than Python API. For the performance issues on AI-based analysis, further study is needed.