• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.1_2
• /
• pp.79-91
• /
• 2006

The intelligent disk can improve the overall performance of the I/O subsystem by processing the I/O operations in the disk side. At present time, however, realizing the intelligent disk seems to be impossible because of the limitation of the I/O subsystem and the lack of the backward compatibility with the traditional I/O interface scheme. In this paper, we proposed new model for the intelligent disk that dynamically optimizes the I/O subsystem using the information that is only related to the physical sector. In this way, the proposed model does not break the compatibility with the traditional I/O interface scheme. For these works, the boosting algorithm that upgrades a weak learner by repeating teaming is used. If the last learner classifies a recent I/O workload as the multimedia workload, the disk reads more sectors. Also, by embedding this functionality as a firmware or a embedded OS within the disk, the overall I/O subsystem can be operated more efficiently without the additional workload.

• 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.

• Journal of KIISE:Computing Practices and Letters
• /
• v.14 no.7
• /
• pp.636-645
• /
• 2008

OneNAND flash is a high-performance hybrid flash memory that combines the advantages of both NAND flash and NOR flash. OneNAND flash has not only all virtues of NAND flash but also greatly enhanced read performance which is considered as a downside of NAND flash. As a result, it is widely used in mobile applications such as mobile phones, digital cameras, PMP, and portable game players. However, most of the general purpose operating systems, such as Linux, can not exploit the read performance of OneNAND flash because of the restrictions imposed by their virtual memory system and block I/O architecture. In order to solve that problem, we suggest a new approach called virtual I/O segment. By using virtual I/O segment, the superior read performance of OneNAND flash can be exploited without modifying the existing block I/O architecture and MTD subsystem. Experiments by implementations show that this approach can reduce read latency of OneNAND flash as much as 54%.

• Journal of KIISE
• /
• v.42 no.2
• /
• pp.169-176
• /
• 2015

The atomic write technique is a good solution to solve the problem of the double write buffer. The atomic write technique needs modified I/O subsystems (i.e., file system and I/O schedulers) and a special SSD that guarantees the atomicity of the write request. In this paper, we propose the writing unit aligned block allocation technique (for EXT4 file system) and the merge prevention of requests technique for the CFQ scheduler. We also propose an atomic write-supporting SSD which stores the atomicity information in the spare area of the flash memory page. We evaluate the performance of the proposed atomic write scheme in MariaDB using the tpcc-mysql and SysBench benchmarks. The experimental results show that the proposed atomic write technique shows a performance improvement of 1.4~1.5 times compared to the double write buffer technique.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.1187-1190
• /
• 1993

The problem of the optimization of fuzzy relational models for dealing with (non-fuzzy) numerical data is investigated. In this context, interfaces optimization assumes particular importance, becoming a determinant factor in what concerns the overall model performance. Considering this, several scenarios for building fuzzy relational models are presented. These are: (i) optimizing I/O interfaces in advance (independently from the linguistic part of the model); (ii) optimizing I/O interfaces in advance and allowing that their optimized parameters may change during the learning of the linguistic part of the model; (iii) build simultaneously both interfaces and the linguistic subsystem; and (iv) build simultaneously both linguistic subsystem and interfaces, now subject to semantic integrity constraints. As linguistic subsystems, both a basic type and an extended versions of fuzzy relation equations are exploited in each one of these scenarios. A comparative analysis of the differ nt approaches is summarized.

• Proceedings of the KSRS Conference
• /
• v.1
• /
• pp.196-199
• /
• 2006

Various communication mechanisms have been developed to acquire a meaningful data from sensors. The key requirement during the sensor data acquisition is determinism and reduction of time dependency. It is a fundermental level of satellite data management for controlling satellite operation software data acquisition from sensors or subsystem. Satellite operation software has various software modules to be operated in addition to data acquisition. Therefore, unnecessary time delay shall be minimized to perform the data acquisition. As the result, interrupt method might be prefered than polling method because the former can decrease the restriction of design during implementation of data acquisition logic. The possible problems while using interrupt method like as interrupt latency caused by delaying of interrupt processing time are analyzed. In this paper, communication mechanism which can be used to interface with satellite computer and subsidary subsystem by using interrupt is presented. As well, time dependency between software scheduling and data acquisition is analyzed.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.28 no.7
• /
• pp.1029-1037
• /
• 2004

High-speed/precision servomechanisms have been widely used in the manufacturing and semiconductor industries. In order to ensure the required high-speed and high-precision specifications in servomechanisms, an integrated design methodology is required, where the interactions between mechanical and electrical subsystems will have to be considered simultaneously. For the first step of the integrated design process, it is necessary to obtain not only strict mathematical models of separate subsystems but also formulation of an integrated design problem. A two-degree-of-freedom controller described in the discrete-time domain is considered as an electrical subsystem in this paper. An accurate identification process of the mechanical subsystem is conducted to verify the obtained mathematical model. Mechanical and electrical constraints render the integrated design problem accurate. Analysis of the system performance according to design and operating parameters is conducted for better understanding of the dynamic behavior and interactions of the servomechanism. Experiments are performed to verify the validity of the integrated design problem in the x-Y positioning system.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.10 no.1
• /
• pp.95-105
• /
• 2006

The speed of hard disk which is based on mechanical operation is more slow than processor. The growth of processor speed is rapid by semiconductor technology, but the growth of disk speed which is based on mechanical operation is not enough. Buffer cache in main memory and disk cache in disk controller have been used in computer system to solve the speed gap between processor and I/O subsystem. In this paper, an efficient buffer cache and disk cache management scheme was proposed to restrict duplicated disk block between buffer cache and disk cache. The performance of the proposed algorithm was evaluated by simulation.

• Aerospace Engineering and Technology
• /
• v.1 no.2
• /
• pp.45-50
• /
• 2002

A conceptual design on the link budget of TC&R RF subsystem which transfers command and telemetry data as RF signal between the ground system and the 2005SAT spacecraft is presented in this paper. In order to perform the analysis of the link budget, we divided the analysis process into two processes, i.e., uplink and downlink process. For the uplink the power flux density at the spacecraft and the margin of the command receiver are calculated. In the case of the downlink the downlink EIRP and the margin of C/ No and Eb / No at the ground station are calculated. Through the uplink performance analysis, the power at the command receiver has well efficient margin, and the margin of C/ No and Eb / No is also fully proper for the downlink case.

• Journal of Korea Society of Industrial Information Systems
• /
• v.18 no.4
• /
• pp.9-18
• /
• 2013

Flash memory is mostly used on smart devices and embedded systems because of its nonvolatile memory, low power, quick I/O, resistant shock, and other benefits. Generally the typical file systems base on the NAND flash memory are YAFFS2, JFFS2, UBIFS, and etc. In this paper, we had variously made an experiment regarding I/O performance using our schemes and the UBIFS of the latest Linux Kernel. The proposed I/O performance analyses were classified as a sequential access and a random access. Our experiment consists of 6 cases using kmalloc(), vmalloc(), and kmem_cache(). As a result of our experiment analyses, the sequential reading and the sequential rewriting increased by 12%, 11% when the Case 2 has applied vmalloc() and kmalloc() to the UBI subsystem and the UBIFS. Also, the performance improved more by 7.82%, 6.90% than the Case 1 at the random read and the random write.