• Journal of Korea Multimedia Society
• /
• v.14 no.5
• /
• pp.669-680
• /
• 2011

R-trees are widely used in various areas such as geographical information systems, CAD systems and spatial databases in order to efficiently index multi-dimensional data. As data sets used in these areas grow in size and complexity, however, range query operations on R-tree are needed to be further faster to meet the area-specific constraints. To address this problem, there have been various research efforts to develop strategies for acceleration query processing on R-tree by using the buffer mechanism or parallelizing the query processing on R-tree through multiple disks and processors. As a part of the strategies, approaches which parallelize query processing on R-tree through Graphics Processor Units(GPUs) have been explored. The use of GPUs may guarantee improved performances resulting from faster calculations and reduced disk accesses but may cause additional overhead costs caused by high memory access latencies and low data exchange rate between GPUs and the CPU. In this paper, to address the overhead problems and to adapt GPUs efficiently, we propose a novel approach which uses a GPU as a buffer to parallelize query processing on R-tree. The use of buffer algorithm can give improved performance by reducing the number of disk access and maximizing coalesced memory access resulting in minimizing GPU memory access latencies. Through the extensive performance studies, we observed that the proposed approach achieved up to 5 times higher query performance than the original CPU-based R-trees.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.11 no.5
• /
• pp.17-30
• /
• 2001

In this paper, we implemented a scalar multiplier needed at an elliptic curve cryptosystem over standard basis in $GF(2^{163})$. The scalar multiplier consists of a radix-16 finite field serial multiplier and a finite field inverter with some control logics. The main contribution is to develop a new fast finite field inverter, which made it possible to avoid time consuming iterations of finite field multiplication. We used an algorithmic transformation technique to obtain a data-independent computational structure of the Extended Euclid GCD algorithm. The finite field multiplier and inverter shown in this paper have regular structure so that they can be easily extended to larger word size. Moreover they can achieve 100% throughput using the pipelining. Our new scalar multiplier is synthesized using Hyundai Electronics 0.6$\mu\textrm{m}$ CMOS library, and maximum operating frequency is estimated about 140MHz. The resulting data processing performance is 64Kbps, that is it takes 2.53ms to process a 163-bit data frame. We assure that this performance is enough to be used for digital signature, encryption & decryption and key exchange in real time embedded-processor environments.

• Journal of KIISE:Computer Systems and Theory
• /
• v.35 no.1
• /
• pp.30-43
• /
• 2008

Memory reference instructions such as loads or stores are critical factors that limit the processing power of processor. The prefetching technique is an effective way to reduce the latency caused from memory access. However, excessively aggressive prefetch leads to cache pollution so as to cancel out the advantage of prefetch. In this study, four filtering schemes have been compared and evaluated which dynamically decide whether to begin prefetch after referring a filtering table to decrease cache pollution. First, A bi-states scheme has been shown to analyze the lock problem of the conventional scheme, this scheme such as conventional scheme used to be N:1 mapping, but it has the two state to 1bit value of each entries. A complete state scheme has been introduced to be used as a reference for the comparative study. A block address lookup scheme has been proposed as the main idea of this paper which exhibits the most exact filtering performance. This scheme has a length of the table the same as the bi-states scheme, the contents of each entry have the fields the same as the complete state scheme recently, never referenced data block address has been 1:1 mapping a entry of the filter table. Experimental results from commonly used general benchmarks and multimedia programs show that average cache miss ratio have been decreased by 10.5% for the block address lookup scheme(BAL) compare to conventional dynamic filter scheme(2-bitSC).

• Journal of the Korean Geotechnical Society
• /
• v.15 no.5
• /
• pp.217-228
• /
• 1999

The three methods of analysis (i) REV(representative elemental volume), (ii) non-REV and (iii) joint network analysis are introduced in this paper to analyze the groundwater flow in jointed rock mass and the inflow into underground excavations. The results from those methods are compared one another to reveal their characteristics by varying the number of joints and the diameter of the opening. The pre-processor, the so-called sequential analysis, is introduced to predict the equivalent hydraulic conductivity of a jointed rock mass having a number of intersecting joints. Using the finite element mesh, joint map and sequential analysis, the equivalent hydraulic conductivities are calculated for all 445 elements. The hydraulic inhomogeneity and the determination of the representative properties of jointed rock masses are discussed. In the REV analysis where the entire rock mass is homogenized through the representative properties, the inflow is increased regularly and consistently by increasing the joint density, the opening size and the conductivity contrast value. Though the non-REV analysis showed irregular variation of the inflow due to the local inhomogeneity allowed to individual elements, the inflow approached the REV results as the characteristic length increases. The joint network analysis showed the most sensitive reaction to the joint density, the opening size and the presence of the network crossing the opening. The reliability of the network analysis depends on the geometric data of individual joints. In view of the limited field data on joint geometry and possible uncertainty the REV and non-REV methods are considered more practical and rational than the joint network analysis.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.43 no.4 s.310
• /
• pp.1-14
• /
• 2006

The indirect branch instruction is a most substantial obstacle in utilizing ILP of modem high performance processors. The target address of an indirect branch has the polymorphic characteristic varied dynamically, so it is very difficult to predict the accurate target address. Therefore the performance of a processor with speculative methodology is reduced significantly due to the many execution cycle delays in occurring the misprediction. We proposed the very accurate and novel indirect branch prediction scheme so called data-dependence based prediction. The predictor results in the prediction accuracy of 98.92% using 1K entries, and. 99.95% using 8K But, all of the proposed indirect predictor including our predictor has a large hardware overhead for restoring expected target addresses as well as tags for alleviating an aliasing. Hence, we propose the scheme minimizing the hardware overhead without sacrificing the prediction accuracy. Our experiment results show that the hardware is reduced about 60% without the performance loss, and about 80% sacrificing only the performance loss of 0.1% in aspect of the tag overhead. Also, in aspect of the overhead of storing target addresses, it can save the hardware about 35% without the performance loss, and about 45% sacrificing only the performance loss of 1.11%.

• Spatial Information Research
• /
• v.12 no.1
• /
• pp.13-27
• /
• 2004

The current industrial development and the increase of population in Daecheong Reservoir basin have produced a rapid increase of wastewater discharge. This has resulted in problem of water quality control and management. Although many efforts have been carried out, reservoir water quality has not significantly improved. In this sense, the development of water quality management system is required to improve reservoir water quality. The goal of this study is to design a GIS-based water quality management system for the scientific water quality control and management in the Daecheong Reservoir. For general water quality analysis, WASP5 model was applied to the Daecheong Reservoir. A sensitivity analysis was made to determine significant parameters and an optimization was made to estimate optimal values. The calibration and verification were performed by using observed water quality data for Daecheong Reservoir. A water quality management system for Daecheong Reservoir was made by connecting the WASP5 model to ArcView. It allows a Windows-based Graphic User Interface(GUI) to implement all operation with regard to water quality analysis. The proposed water quality management system has capability for the on-line data process including water quality simulation, and has a post processor far the reasonable visualization for various output. The modeling system in this study will be an efficient NGIS(National Geographic Information System) far planning of reservoir water quality management.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.5
• /
• pp.97-105
• /
• 2017

An air-burst munition is limited in space, so there is a limit on the size of the fuze and the amount of ammunition. In order to increase a firepower to a target with limited ammunition, it is necessary to concentrate the firepower on the ground instead of the omnidirectional explosion after flying to the target. This paper explores the design and verification of a ground-detection sensor that detects the direction of the ground and determines the flight-distance of an air-burst munition using a single axis geomagnetic sensor. Prior to the design of the ground detection sensor, a geomagnetic sensor model mounted on the spinning air-burst munition is analyzed and a ground-detection algorithm by simplifying this model is designed. A high speed rotating device to simulate a rotation environment is designed and a geomagnetic sensor and a remote-recording system are fabricated to obtain geomagnetic data. The ground detection algorithm is verified by post-processing the acquired geomagnetic data. Taking miniaturization and low-power into consideration, the ground detection sensor is implemented with analog devices and the processor. The output signal of the ground detection sensor rotating at an arbitrary rotation speed of 200 Hz is connected to the LED (Light Emitting Diode) in the high speed rotating device and the ground detection sensor is verified using a high-speed camera.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.28 no.4
• /
• pp.337-346
• /
• 1992

Hydroacoustic surveys were conducted in the East China Sea, in the summers of 1990-1991 to investigate the distribution and migration behavior of fish, such as the diel changes in the distributions of fish, the thermoselection behavior of fish, and the fish reactions to a surveying vessel. The hydroacoustic observations were taken with a scientific echo sounder operating at 50kHz and a microcomputer-based echo processor. Fish samples were collected by bottom trawling and temperature was measured with a DBT system. The patterns of fish distributions were compared with the vertical profiles of water temperature. The results obtained can be summarized as follows: 1. The time series of hydroacoustic observations on the downward migration at dawn in the central region of East China Sea showed that the migration rate was 0.24 m/min. In this region, most of the fish collected by bottom trawling during the surveys were squid (Photologio edulis f. budo) and horse mackeral (Trachurus japonicus). 2. The hydroacoustic observations, which together associated with temperature data, indicated that squid and horse mackeral concentrated nocturally in a narrow vertical band of thermocline, particularly in summer when the survey region was strongly stratified. This result suggest that the nocturnal vertical distribution of these species evidently is controlled by temperature. 3. When the survey vessel, that is running at a speed of 11 knots, has suddenly stopped, the fish which concentrated beneath the transducer showed a strong avoidance reaction in the form of rapid downward migration. After a few minutes, the descending reaction disappeared and the fish slowly began the upward migration toward their original swimming positions. Trawl data suggest that the fish, which showed the avoidance reaction, was Liparis tessellatus.

• Journal of KIISE:Computer Systems and Theory
• /
• v.27 no.8
• /
• pp.719-729
• /
• 2000

Prefetching aims at reducing memory latency by fetching, in advance, data that are likely to be requested by the processor in a near future. The effectiveness of prefetching is determined by how accurate the prediction on the needed instructions and data is. Most previous studies on prefetching were limited to proposing a particular prefetch scheme and its performance evaluation, paying little attention to theoretical aspects of prefetching. This paper focuses on the theoretical aspects of instruction prefetching. For this purpose, we propose a clairvoyant prefetch model that makes use of perfect history information. Based on this theoretical model, we analyzed upper limits on the prefetch prediction accuracies of the SPEC benchmarks. The results show that the prefetch prediction accuracy is very high when there is no cache. However, as the size of the instruction cache increases, the prefetch prediction accuracy drops drastically. For example, in the case of the spice benchmark, the prefetch prediction accuracy drops from 53% to 39% when the cache size increases from 2Kbyte to 16Kbyte (assuming 16byte block size). These results indicate that as the cache size increases, most localities are captured by the cache and that instruction prefetching based on the information extracted from the references that missed in the cache suffers from prediction inaccuracies

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.8B
• /
• pp.1460-1468
• /
• 2000

The goal of this research is the real-time implementation of MPEG-1 Layer III audio decoder using the fixed-point digital signal processor of TMS320C6201 The main job for this work is twofold: one is to convert floating-point operation in the decoder into fixed-point operation while maintaining the high resolution, and the other is to optimize the program to make it run in real-time with memory size as small as possible. We, especially, devote much time to the descaling module in the decoder for conversion of floating-point operation into fixed-point operation with high accuracy. The inverse modified cosine transform(IMDCT) and synthesis polyphase filter bank modules are optimized in order to reduce the amount of computation and memory size. After the optimization process, in this paper, the implemented decoder uses about 26% of maximum computation capacity of TMS320C6201. The program memory, data ROM, data RAM used in the decoder are about 6.77kwords, 3.13 kwords and 9.94 kwords, respectively. Comparing the PCM output of fixed-point computation with that of floating-point computation, we achieve the signal-to-noise ratio of more than 60 dB. A real-time operation is demonstrated on the PC using the sound I/O and host communication functions in the EVM board.