• Journal of KIISE:Computer Systems and Theory
• /
• v.28 no.5
• /
• pp.213-217
• /
• 2001

Excessive memory buffer requirement in continuous media playback is a serious impediment of wide spread usage of on-line multimedia service. Skewed access frequency of available video files provides an opportunity of re-using the date blocks which has been loaded by one session for later usage. We present novel algorithm which minimizes the buffer requirement in multiple sessions of multimedia playbacks. In continuous media playback originated from the disk, a certain amount of memory buffer is required to synchronize asynchronous disk. Read operation and synchronous playback operation. As aggregate playback bandwodth increases, larger amount of buffer needs to be allocated for this synchronization purpose. The focus of this work is to study the asymptotic behavior of the synchronization buffer requirement and to develop an algorithm coping with this excessive buffer requirement under bandwidth congestioon. We argue that in a large scale continuous media server, it may not be necessary to read the blocks for each session directly from the disk. The beauty of our work lies in the fact that it dynamically adapts to disk utilization of the server and finds the optimal way of servicinh the individual sessions while minimizing the overall buffer space requirement. Optimality of the proposed algorithm is shown by proof. The effectiveness and performance of the proposed scheme is examined via simulation.

• Journal of KIISE:Computer Systems and Theory
• /
• v.30 no.12
• /
• pp.756-771
• /
• 2003

Digital Video Library System which manages a large amount of multimedia information requires efficient and effective retrieval methods. In this paper, we propose and implement a new video search and retrieval algorithm that compares the query video shot with the video shots in the archives in terms of foreground object, background image, audio, and its context. The foreground object is the region of the video image that has been changed in the successive frames of the shot, the background image is the remaining region of the video image, and the context is the relationship between the low-level features of the adjacent shots. Comparing these features is a result of reflecting the process of filming a moving picture, and it helps the user to submit a query focused on the desired features of the target video clips easily by adjusting their weights in the comparing process. Although the proposed search and retrieval algorithm could not totally reflect the high level semantics of the submitted query video, it tries to reflect the users' requirements as much as possible by considering the context of video clips and by adjusting its weight in the comparing process.

• Journal of KIISE:Computer Systems and Theory
• /
• v.30 no.12
• /
• pp.708-713
• /
• 2003

For many years clustered heterogeneous web server architecture has been formed on the internet because the explosive internet services and the various quality of requests. The critical point in cluster environment is the mapping schemes of request to server. and recently this is the main issue of internet architecture. The topic of previous mapping methods is to assign equal loads to servers in cluster using the number of requests. But recent growth of various services makes it hard to depend on simple load balancing to satisfy appropriate latency. So mapping based on requested content to decrease response time and to increase cache hit rates on entire servers - so called “content-based” mapping is highly valuated on the internet recently. This paper proposes Prioritized Highest Random Weight mapping(PHRW mapping) that improves content-based mapping to properly fit in the heterogeneous environment. This mapping scheme that assigns requests to the servers with priority, is very effective on heterogeneous web server cluster, especially effective on decreasing latency of reactive data service which has limit on latency. This paper have proved through algorithm and simulation that proposed PHRW mapping show higher-performance by decrease in latency.

• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.7
• /
• pp.413-420
• /
• 2006

The speed of present-day network technology exceeds a gigabit and is developing rapidly. When using TCP/IP in these high-speed networks, a high load is incurred in processing TCP/IP protocol in a host CPU. To solve this problem, research has been carried out into TCP/IP Offload Engine (TOE). The TOE processes TCP/IP on a network adapter instead of using a host CPU; this reduces the processing burden on the host CPU. In this paper, we developed two software-based TOEs. One is the TOE implementation using an embedded Linux. The other is the TOE implementation using Lightweight TCP/IP (lwIP). The TOE using an embedded Linux did not have the bandwidth more than 62Mbps. To overcome the poor performance of the TOE using an embedded Linux, we ported the lwIP to the embedded system and enhanced the lwIP for the high performance. We eliminated the memory copy overhead of the lwIP. We added a delayed ACK and a TCP Segmentation Offload (TSO) features to the lwIP and modified the default parameters of the lwIP for large data transfer. With the aid of these modifications, the TOE using the modified lwIP shows a bandwidth of 194 Mbps.

• Journal of KIISE:Computer Systems and Theory
• /
• v.29 no.11
• /
• pp.589-600
• /
• 2002

Deformable models offer an attractive approach for extracting three-dimensional boundary structures from volumetric images. However, conventional deformable models have three major limitations - sensitive to initial condition, difficult to represent complex boundaries with severe object concavities and protrusions, and self-intersective between model elements. This paper proposes a deformable model that is effective to extract geometrically complex boundary surfaces by improving away the limitations of conventional deformable models. First, the proposed deformable model resamples its elements hierarchically based on volume image pyramid. The hierarchical resampling overcomes sensitivity to initialization by extracting the boundaries of objects in a multiscale scheme and enhances geometric flexibility to be well adapted to complex image features by refining and regularizing the size of model elements based on voxel size. Second, the physics-based formulation of our model integrates conventional internal and external forces, as well as a non-self-intersecting force. The non-self-intersecting force effectively prevents collision or crossing over between non-neighboring model elements by pushing each other apart if they are closer than a limited distance. We show that the proposed model successively extracts the complex boundaries including severe concavities and protrusions, neither depending on initial position nor causing self-intersection, through the experiments on several computer-generated volume images and brain MR volume images.

• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.7
• /
• pp.370-379
• /
• 2006

Computational grid provides the environment which integrates v 따 ious computing resources. Grid environment is more complex and various than traditional computing environment, and consists of various resources where various software packages are installed in different platforms. For more efficient usage of computational grid, therefore, some kind of integration is required to manage grid resources more effectively. In this paper, a global scheduler is suggested, which integrates grid resources at meta level with applying various scheduling policies. The global scheduler consists of a mechanical part and three policies. The mechanical part mainly search user queues and resource queues to select appropriate job and computing resource. An algorithm for the mechanical part is defined and optimized. Three policies are user selecting policy, resource selecting policy, and executing policy. These can be defined newly and replaced with new one freely while operation of computational grid is temporarily holding. User selecting policy, for example, can be defined to select a certain user with higher priority than other users, resource selecting policy is for selecting the computing resource which is matched well with user's requirements, and executing policy is to overcome communication overheads on grid middleware. Finally, various algorithms for user selecting policy are defined only in terms of user fairness, and their performances are compared.

• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.12
• /
• pp.894-906
• /
• 2006

There are many difficulties to develop a mobile contents due to many constraints on mobile environments. It is difficult to make a good mobile contents with only visual reduction of existing contents on wire Internet. Therefore, it is essential to devise the data representation and to develop the authoring tool to meet the needs of the mobile contents market. We suggest the compact mobile contents to learn Chinese characters and developed its authoring tool. The animation which our system produces is realistic as if someone writes letters with pen or brush. Moreover, our authoring tool makes a user generate a Chinese character animation easily and rapidly although she or he has not many knowledge in computer graphics, mobile programming or Chinese characters. The method to generate the stroke animation is following: We take basic character shape information represented with several contours from TTF(TrueType Font) and get the information for the stroke segmentation and stroke ordering from simple user input. And then, we decompose whole character shape into some strokes by using polygonal approximation technique. Next, the stroke animation for each stroke is automatically generated by the scan line algorithm ordered by the stroke direction. Finally, the ordered scan lines are compressed into some integers by reducing coordinate redundancy As a result, the stroke animation of our system is even smaller than GIF animation. Our method can be extended to rendering and animation of Hangul or general 2D shape based on vector graphics. We have the plan to find the method to automate the stroke segmentation and ordering without user input.

• Journal of KIISE:Computer Systems and Theory
• /
• v.32 no.11_12
• /
• pp.541-556
• /
• 2005

The memory access latency of the system has been a primary factor of performance degradation in single-processor system and multi-processor system. The remote memory access latency takes a lot of overhead over the local memory access latency especially in the distributed shared-memory system. To resolve this problem, the multi-level cache architecture that contains a remote cache in the multi-processor system has been proposed. In this paper, we propose a new cache replacement policy that improves the performance of the multi-processor system with the remote cache. If the multi-level cache keeps the multi-level inclusion(MLI) property and uses the LRU(Least Recently Used) cache replacement policy, the LRU information of the higher-level cache(a processor cache) would be different with that of the lower-level cache(a remote cache). In this situation, the replacement of a remote cache line can induce the exchange of a processor cache line that is used by the processor. It is a main factor of performance degradation in a whole system. To alleviate this disadvantage of the LRU replacement polity, the new policy analyses tht processor's remote memory access pattern of each node and uses this information to reduce the number of invalidations of the useful cache line in the higher-level cache. The new replacement policy of the remote cache can improve the performance by $3.5\%$ in maximum and $2.5\%$ in average on SPLASH-2 benchmarks, compared to the general LRU cache replacement policy.

• 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

• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.7
• /
• pp.429-439
• /
• 2006

A desktop grid, which is a computing grid composed of idle computing resources in a large network of desktop computers, is a promising platform for compute-intensive distributed computing applications. However, due to reliability and unpredictability of computing resources, effective scheduling of parallel computing applications on such a platform is a difficult problem. This paper proposes a new scheduling method aimed at reducing the total execution time of a parallel application on a desktop grid. The proposed method is based on utilizing the histories of execution behavior of individual computing nodes in the scheduling algorithm. In order to test out the feasibility of this idea, execution trace data were collected from a set of 40 desktop workstations over a period of seven weeks. Then, based on this data, the execution of several representative parallel applications were simulated using trace-driven simulation. The simulation results showed that the proposed method improves the execution time of the target applications significantly when compared to previous desktop grid scheduling methods. In addition, there were fewer instances of application suspension and failure.