• Journal of the Korea Society of Computer and Information
• /
• v.9 no.4 s.32
• /
• pp.173-178
• /
• 2004

A network of Asynchronous Transfer Mode (ATM) will be required to carry the traffics(CVR, VBR, UBR. ABR) generated by a wide range of services ATM services the Quality-of-Service (QoS) management of traffice sources and bandwidth. Besides efficiency and throughput, the security services are achieved in the traffic sent in ATM network. In this paper, the scheduler evaluate and the packets sent in ATM security group. The scheduler transmits the safty packet, drop the unsafty packet and evaluate mark packet as the requirement of the delay. In this paper, we propose the scheduling algorithm of mark packet which evaluates the packet. The suggested model performance of the firewall switch is estimate simulation in terms of the delay by computer.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.11a
• /
• pp.403-405
• /
• 2009

통방융합 환경에서 Killer 서비스로 각광을 받고 있는 VOD(Video On Demand)서비스에서 I/O 병목현상은 VOD 서버의 오 동작 및 성능 저하의 주요 원인이 되고 있다. 본 논문에서는 이런 I/O 병목 현상을 개선하여 입출력 효율이 좋은 고성능 VOD 솔루션을 제안한다. 제안된 솔루션은 대용량 더블 버퍼를 구성하여 하나의 버퍼로 클라이언트에 데이터를 전송하고 있는 사이에, 나머지 다른 버퍼에서 스토리지에서 전송되는 데이터를 버퍼에 저장 하여, 디스크 접근 시 한번에 보다 많은 데이터를 읽음으로써 연속적인 정보를 가져올때 빈번하게 하드디스크의 접근을 줄임으로서 끊김없는 전송을 가능하게 한다. 또한 다수의 사용자가 동시 접근 시 데이터 충돌을 방지하고, 스토리지에 순차적으로 연속 접근하도록 접근 발생 시간에 따라 우선 순위 인덱스를 할당하고 회수하도록 스토리지 접근 스케쥴러를 고안 하였다. 제안된 솔루션의 유효성을 검증하기 위해 SD급 콘텐츠에 대해 솔루션의 Throughoutput 처리량을 벤치마킹 테스트로 검증을 하였다. 테스트 결과 MPEG-2 SD급 영상에대해 Raid 5에서 최대 1000 스트리밍을 전송 할 수 있음을 확인 하였다.

• Journal of Digital Contents Society
• /
• v.10 no.1
• /
• pp.55-60
• /
• 2009

Due to the development of the Internet, there are a lot of information around, and the amount of this information is growing exponentially. The information management systems, which are built to manage the numerous amount of information, helps the user retrieve information more accurately and efficiently. However, mobile systems and its built-in file systems, lack in information management and has a limited processing power for real-time data. This paper suggests the middleware system for effective management of large data and enabling real-time data processing. To show the possibility of middleware, the paper implemented a real-time alarm scheduler, which links web database systems and mobile phones.

• Journal of the Korea Society of Computer and Information
• /
• v.1 no.1
• /
• pp.147-158
• /
• 1996

This paper proposed a concurrency control structure based on specialized data flow graphs that was analysed a run-time concurrency control activity to be integrated with the task scheduler Data were viewed as flowing on the arcs from one node to another in a stream of discrete to tokens. The network that Is based upon the Entity-Relationship model, can be viewed a fixed problems used query tokens as a data flow graph. The performance was measured used in the various expriments compared the overall performance of the different concurrency control methods, DBFG (DataBase Flow graphs) scheduling had the knowledge to obtain better performance than 2PL in a distributed environment.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.8
• /
• pp.79-87
• /
• 2010

It is widely accepted that the coverage with high user densities in mobile multimedia environments can only be achieved with small cell such as micro- and pico-cell. If handover events occur during the transmission of multimedia, the efficient resource reservation and handover methods are necessary in order to maintain the same QoS of transmitted multimedia traffic because the QoS may be defected by some delay and information loss. In this paper, we propose a resource allocation method in the next generation mobile communication systems, in which the resource allocation process has a tight relation with call admission, call load, and packet scheduling. The simulation results show that our proposed method provides a excellent performance.

• Journal of Korea Society of Industrial Information Systems
• /
• v.4 no.2
• /
• pp.44-50
• /
• 1999

This paper presents a set of techniques to automatically find rate optimal or near rate optimal implementation of shift-invariant flow graphs on pipelined processor, in which pipeline processor has multiple accumulators and internal datapaths. In such case, the problem to be addressed is the scheduling of multiple instruction streams which control all of the pipeline stages. The goal of an automatic scheduler in this context is to rearrange the order of instructions such that they are executed with minimum iteration period between successive iteration of defining flow graphs. The scheduling algorithm described in this paper also focuses on the problem of removing the hazards due to inter-instruction dependencies.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.04a
• /
• pp.12-14
• /
• 2014

하드웨어가 해저드(hazard) 검출을 지원하지 않는 멀티이슈 VLIW 프로세서의 성능을 높이기 위해서는 컴파일러가 명령어 의존성과 하드웨어 자원의 제약을 지키는 범위 안에서 최대한 명령어수준 병렬성(ILP)을 활용하는 것이 중요하다. 기본 블록(basic block) 스케쥴링은 Branch 등 제어 흐름(control flow)의 경계를 넘어선 스케쥴링을 행하지 않아 그 효과가 제한적이다. 소프트웨어 파이프라이닝(software pipelining)은 루프(loop)의 경계를 허물어 여러반본(iteration)의 명령어가 동시에 수행되도록 하는 것으로 모듈로 스케쥴링(modulo scheduling)은 그 중에 한 범주의 스케쥴링 기법들을 일컫는다. 본 연구에서는 그 중 한가지인 스윙 모듈로 스케쥴러(swing modulo scheduler)[1]를 구현하여 그 효과를 알아보고자 한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.448-450
• /
• 2019

Multipath TCP (MPTCP) is a standardized transport layer protocol for maximizing the use of finite network resources by using multiple interfaces simultaneously. If the characteristics of each path are the same, there is an advantage in terms of stability and bandwidth utilization compared to the existing single TCP. However, if the path characteristics are different, the performance is lower than that of a single TCP. There are many complex reasons for this, but one of the biggest impacts is the bufferbloat, which dramatically increases the latency. In this paper, we implemented an algorithm that improved MPTCP performance degradation due to bufferbloat in Linux - based testbed and compared performance with existing MPTCP scheduler.

• Journal of the Korean Society of Industry Convergence
• /
• v.27 no.1
• /
• pp.87-95
• /
• 2024

This study is on modulo scheduling algorithms for multicore processor in machine learning applications. Machine learning algorithms are designed to perform a large amount of operations such as vectors and matrices in order to quickly process large amounts of data stream. To support such large amounts of computations, processor architectures to support applications such as artificial intelligence, neural networks, and machine learning are designed in the form of parallel processing such as multicore. To effectively utilize these multi-core hardware resources, various compiler techniques are being used and studied. In this study, among these compiler techniques, we analyzed the modular scheduler, which is especially important in one core's computation pipeline. This paper looked at and compared the iterative modular scheduler and the swing modular scheduler, which are the most widely used and studied. As a result, both schedulers provided similar performance results, and when measuring register pressure as an indicator, it was confirmed that the swing modulo scheduler provided slightly better performance. In this study, a technique that divides recurrence edge is proposed to improve the minimum initiation interval of the modulo schedulers.

• Journal of Korea Society of Industrial Information Systems
• /
• v.16 no.1
• /
• pp.1-8
• /
• 2011

Efficient power management plays a crucial role to strengthen competitiveness in the market of portable mobile commodities. This paper presents a proactive power management technique, called by Energy-Aware Scheduling policY (EASY), to exploit the sleep time information of running applications. Different from previous power management approaches focusing on power conservation in standby mode, the proposed scheme characterizes each application program's operational characteristic in active mode by observing how long the task stays in sleep state of CPU scheduler. Based on the measured sleep time, the proposed EASY speculates an adequate CPU clock frequency according to the current CPU workload and scales the frequency directly to the predicted one. Experimental results show that the proposed scheme reduces the power consumption by 10-30% on average compared to traditional DPM approach, with a minimal impact on the performance overhead.