• ETRI Journal
• /
• v.20 no.4
• /
• pp.301-326
• /
• 1998

In this paper, we have modeled and evaluated a new parallel processing system called Scalable Parallel computer Architecture based on Xbar (SPAX) for commercial applications. SMP systems are widely used as servers for commercial applications; however, they have very limited scalability. SPAX cost-effectively overcomes the SMP limitation by providing both scalability and application portability. To investigate whether the new architecture satisfies the requirements of commercial applications, we have built a system model and a workload model. The results of the simulation study show that the I/O subsystem becomes the major bottleneck. We found that SPAX can still meet the I/O requirement of the OLTP workload as it supports flexible I/O subsystem. We also investigated what will be the next most important bottleneck in SPAX and how to remove it. We found that the newly developed system network called Xcent-Net will not be a bottleneck in the I/O data path. We also show the optimal configuration that is to be considered for system tuning.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.14 no.2
• /
• pp.63-69
• /
• 2019

Recently, ultra-low latency flash storage devices such as Z-SSD and Optane SSD were introduced with the significant technological improvement in the storage devices which provide much faster response time than today's other NVMe SSDs. With such ultra-low latency, $10{\mu}s$, storage devices the cost of context switch could be an overhead during interrupt-driven I/O completion process. As an interrupt-driven I/O completion process could bring an interrupt handling overhead, polling or hybrid-polling for the I/O completion is known to perform better. In this paper, we analyze tail latency problem in a polling process caused by process scheduling in data center environment where multiple applications run simultaneously under one system and we introduce our adaptive polling selection technique which dynamically selects efficient processing method between two techniques according to the system's conditions.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.11
• /
• pp.2701-2710
• /
• 1997

Recursive circulant graph has recently developed as a new model of multiprocessors, and drawn considerable attention to supercomputing, In this paper, we investigate the routing of a message i recursive circulant, that is a key to the performance of this network. On recursive circulant network, we would like to transmit m packets from a source node to a destination node simultaneously along paths, where the ith packet will traverse along the ith path $(o{\leq}i{\leq}m-1)$. In oder for all packets to arrive at the destination node quickly and securely, the ith path must be node-disjoint from all other paths. For construction of these paths, employing the Hamiltonian Circuit Latin Square(HCLS), a special class of $(n{\times}n)$ matrices, we present $O(n^2)$ parallel routing algorithm on recursive circulant network.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.27 no.9
• /
• pp.1351-1363
• /
• 1990

In this paper, a reliable control system structured with dual CPU modules and dual I/O modules is implemented as a means of achieving a highly reliable fault tolerant control system. For this, faults in the system modules are first examined, and a fault detection technique consisting of self diagnostic, comparison process, and exception processing is applied. Self diagnostic is used to locate which components in the modules have been failed, while comparison process is to cmpare control outputs computed by both CPU modules and protect the plant from malfunction by blocking failed control outputsin advance. Finally exception processing is used to determine the faults that are not detected immediately by the self diagnostic and comparison process, e.g. bus error processing when acknowledge signal for data transfer is not activeted in the I/O modules. Also reliability analysis is conducted for the discrete time Markov model with dual structure. It is shown quantitatively that the reliability is improved in the control system with dual structure in comparison with a system with single module structure.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.11a
• /
• pp.18-20
• /
• 2013

가상화 기술은 다양한 분야에서 컴퓨팅 환경의 자원 활용성을 높이기 위해 사용되고 있다. 가상화 환경의 성능을 향상시키기 위해 여러 가지 연구가 진행되었고 프로세서/메모리 가상화의 경우 비약적인 발전이 있었다. 하지만 빈번한 입출력 워크로드에서 장치 가상화는 아직까지 모드 전환에 의한 성능 저하로 연구가 더 필요한 실정이다. 이에 본 논문에서는 입출력 중심 워크로드의 효과적인 실행을 위하여 커널의 공유 메모리 공간과 에뮬레이터 I/O 서비스 스레드의 폴링을 이용하여 게스트에서 I/O 요청 시에 발생하는 모드 전환을 제거하였고 성능 개선을 확인하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2007.11a
• /
• pp.579-582
• /
• 2007

최근 들어 더욱 UCC(User Created Contents)등과 같은 대용량 멀티미디어(multimedia) 서비스에 대한 요구가 나날이 증가되면서 부하분산에 중점을 둔 웹 클러스터링 시스템(Web Clustering System) 에서 기존의 작은 크기의 스트림 데이터(Stream Data)나 조금 더 다양한 데이터를 위한 읽기 성능을 대용량 데이터에 초점을 맞춘 방안으로 최적화 시키는 것이 중요시되고 있다. 본 논문에서는 대용량 멀티미디어를 중심으로 실제 서비스시 간과 되어질 수 있는 운영체제(Operating System, O/S)에서의 I/O 인식, 디스크 제어 프로그램에서의 I/O, 웹 클러스터의 부하분산정책의 파라미터(Parameter)를 개선함으로써 읽기성능 향상 방안을 제시한다.

• The KIPS Transactions:PartC
• /
• v.13C no.2 s.105
• /
• pp.167-170
• /
• 2006

Most wavelength assignment algorithms assume that every node has infinite ADMs and I/O blocking is excluded. Furthermore wavelengths continue to occur intermittently in the network using existing algorithms. This can result in increased link blocking under dynamic traffic circumstances. In audition, it can create time-complexity problems such as O(W $N^3$) in the worst case scenario. In this paper, we propose a new wavelength assignment algorithm which has time-complexity of O(W $N^2$) and considers both I/O and link blocking. The basic idea is to maximize the number of links where wavelengths will be assigned continuously after present assignment. As a result, the number of intermittent wavelengths is minimized, and blocking probabilities are decreased.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2002.10a
• /
• pp.536-539
• /
• 2002

In this paper, we developed the automatic optical fiber aligner by image processing and automatic loading system. Optical fiber is indispensable for optical communication systems that transmit large volumes of data at high speed, but super-precision technology in sub-micron units is required for optical axis adjustment, we have developed 6-axis micro stage system for I/O optical fiber arrays, the initial automatic aligning system/software for a input optical array by the image processing technique, fast I/O-synchronous aligning strategy, the automatic loading/unloading system and the automatic UV bonding mechanism. In order to adjust the alignment it used on PC based motion controller, a $10\mu\textrm{mm}$ repeat-detailed drawing of automatic loading system is developed by a primary line up for high detailed drawing. Also, at this researches used the image processing system and algorithm instead of the existing a primary hand-line up. and fiber input array and waveguide chip formed in line by automatic. Therefore, the developed and manufactured optical aligning system in this research fulfills the great role of support industry for major electronics manufacturers, telecommunications companies, universities, government agencies and other research institutions.

• 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:Computing Practices and Letters
• /
• v.12 no.5
• /
• pp.312-325
• /
• 2006

Integration applications, such as EAI, B2Bi, need stable massive data processing systems during overload state cause by service request congestion in a short period time. In this paper, we propose the PLC (Peak Load Control)-based Worker-Linker pattern, which can effectively and stably process massive I/O transactions in spite of overload state generated by service request congestion. This pattern uses the delay time algorithm for the PLC mechanism. In this paper, we also show the example of applying the pattern to business-business integration framework and the experimental result for proving the stability of performance. According to our experiment result, the proposed delay time algorithm can stably control the heavy overload after the saturation point and has an effect on the controlling peak load.