• KIISE Transactions on Computing Practices
• /
• v.22 no.10
• /
• pp.497-503
• /
• 2016

Emerging next-generation storage technologies such as non-volatile memory will help eliminate almost all of the storage latency that has plagued previous storage devices. In conventional storage systems, the latency of slow storage devices dominates access latency; hence, software efficiency is not critical. With low-latency storage, software costs can quickly dominate memory latency. Hence, researchers have proposed the memory mapped file I/O to avoid the software overhead. Mapping a file into the user memory space enables users to access the file directly. Therefore, it is possible to avoid the complicated I/O stack. This minimizes the number of user/kernel mode switchings. In addition, there is no data copy between kernel and user areas. Despite of the benefits in the memory mapped file I/O, its overhead still needs to be addressed, as the existing mechanism for the memory mapped file I/O is designed for slow block devices. In this paper, we identify the overheads of the memory mapped file I/O via experiments.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.3
• /
• pp.68-74
• /
• 2009

In this paper, we propose an effective memory reduction algorithm to reduce the amount of reference frame buffer and memory bandwidth in video encoder and decoder. In general video codecs, decoded previous frames should be stored and referred to reduce temporal redundancy. Recently, reference frames are recompressed for memory efficiency and bandwidth reduction between a main processor and external memory. However, these algorithms could hurt coding efficiency. Several algorithms have been proposed to reduce the amount of reference memory with minimum quality degradation. They still suffer from quality degradation with fixed-bit allocation. In this paper, we propose an adaptive block-based min-max quantization that considers local characteristics of image. In the proposed algorithm, basic process unit is $8{\times}8$ for memory alignment and apply an adaptive quantization to each $4{\times}4$ block for minimizing quality degradation. We found that the proposed algorithm can obtain around 1.7% BD-bitrate gain and 0.03dB BD-PSNR gain, compared with the conventional fixed-bit min-max algorithm with 37.5% memory saving.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2012.08a
• /
• pp.115-116
• /
• 2012

The demand for flexible electronic systems such as wearable computers, E-paper, and flexible displays has increased due to their advantages of excellent portability, conformal contact with curved surfaces, light weight, and human friendly interfaces over present rigid electronic systems. This seminar introduces three recent progresses that can extend the application of high performance flexible inorganic electronics. The first part of this seminar will introduce a RRAM with a one transistor-one memristor (1T-1M) arrays on flexible substrates. Flexible memory is an essential part of electronics for data processing, storage, and radio frequency (RF) communication and thus a key element to realize such flexible electronic systems. Although several emerging memory technologies, including resistive switching memory, have been proposed, the cell-to-cell interference issue has to be overcome for flexible and high performance nonvolatile memory applications. The cell-to-cell interference between neighbouring memory cells occurs due to leakage current paths through adjacent low resistance state cells and induces not only unnecessary power consumption but also a misreading problem, a fatal obstacle in memory operation. To fabricate a fully functional flexible memory and prevent these unwanted effects, we integrated high performance flexible single crystal silicon transistors with an amorphous titanium oxide (a-TiO2) based memristor to control the logic state of memory. The $8{\times}8$ NOR type 1T-1M RRAM demonstrated the first random access memory operation on flexible substrates by controlling each memory unit cell independently. The second part of the seminar will discuss the flexible GaN LED on LCP substrates for implantable biosensor. Inorganic III-V light emitting diodes (LEDs) have superior characteristics, such as long-term stability, high efficiency, and strong brightness compared to conventional incandescent lamps and OLED. However, due to the brittle property of bulk inorganic semiconductor materials, III-V LED limits its applications in the field of high performance flexible electronics. This seminar introduces the first flexible and implantable GaN LED on plastic substrates that is transferred from bulk GaN on Si substrates. The superb properties of the flexible GaN thin film in terms of its wide band gap and high efficiency enable the dramatic extension of not only consumer electronic applications but also the biosensing scale. The flexible white LEDs are demonstrated for the feasibility of using a white light source for future flexible BLU devices. Finally a water-resist and a biocompatible PTFE-coated flexible LED biosensor can detect PSA at a detection limit of 1 ng/mL. These results show that the nitride-based flexible LED can be used as the future flexible display technology and a type of implantable LED biosensor for a therapy tool. The final part of this seminar will introduce a highly efficient and printable BaTiO3 thin film nanogenerator on plastic substrates. Energy harvesting technologies converting external biomechanical energy sources (such as heart beat, blood flow, muscle stretching and animal movements) into electrical energy is recently a highly demanding issue in the materials science community. Herein, we describe procedure suitable for generating and printing a lead-free microstructured BaTiO3 thin film nanogenerator on plastic substrates to overcome limitations appeared in conventional flexible ferroelectric devices. Flexible BaTiO3 thin film nanogenerator was fabricated and the piezoelectric properties and mechanically stability of ferroelectric devices were characterized. From the results, we demonstrate the highly efficient and stable performance of BaTiO3 thin film nanogenerator.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.44 no.2
• /
• pp.72-85
• /
• 2007

The development of memory design and process technology enabled the production of high density memory. However, this increased the complexity of the memory making memory testing more complicated, and as a result, it brought about an increase in memory testing costs. Effective memory test algorithm must detect various types of defects within a short testing time, and especially in the case of port memory test algorithm, it must be able to detect single port memory defects, and all the defects in the dual port memory. The March A2PF algorithm proposed in this paper is an effective test algorithm that detects all types of defects relating to the duel port and single port memory through the short 18N test pattern.

• Journal of Internet of Things and Convergence
• /
• v.9 no.1
• /
• pp.19-24
• /
• 2023

Recently, with the recent rapid development of memory technology, various types of memory are developed and are used to improve processing speed in data management systems. In particular, NAND flash memory is used as a main media for storing data in memory-based storage devices because it has a nonvolatile characteristic that it can maintain data even at the power off state. However, since the recently studied memory-based storage device consists of various types of memory such as MRAM and PRAM as well as NAND flash memory, research on memory management technology is needed to improve data processing performance and efficiency of media in a storage system composed of different types of memories. In this paper, we propose a memory mapping scheme thought technique for efficiently managing data in the storage device composed of various memories for data management. The proposed idea is a method of managing different memories using a single mapping table. This method can unify the address scheme of data and reduce the search cost of data stored in different memories for data tiering.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.49 no.1
• /
• pp.47-52
• /
• 2012

A power amplifier is one of important factors for basestation's efficiency and the researches for efficency enhancement focus Doherty amplifier structure with GaN power devices in these days. A memory effect of Doherty amplifier affect operation characteristics for linearity and efficiency. This paper reports on electrothermal nonlinearity modeling and compensation for GaN Doherty amplifier's distortion. Also this paper reports on the dynamic expression of the instantaneous junction temperature as a function of the instantaneous dissipated power. We design distortion model for GaN Doherty amplifier and predistortion compensator for electrothermal memory effect from the proposed behavior model parameters. The simulations was evaluated by ADS Tools and GaN Doherty amplifier with 37dBm. The GaN Doherty amplifier with compensator enhanced about 16dB than without electrothemal memory effect compensator in 2-tone output spectrum.

• Journal of Convergence for Information Technology
• /
• v.11 no.11
• /
• pp.44-50
• /
• 2021

Recently, enterprise storage systems that require large-capacity storage devices to accommodate big data have used large-capacity flash memory-based storage devices with high density compared to cost and size. This paper proposes a high-efficiency life prediction method with slope descent to maximize the life of flash memory media that directly affects the reliability and usability of large enterprise storage devices. To this end, this paper proposes the structure of a matrix for storing metadata for learning the frequency of defects and proposes a cost model using metadata. It also proposes a life expectancy prediction policy in exceptional situations when defects outside the learned range occur. Lastly, it was verified through simulation that a method proposed by this paper can maximize its life compared to a life prediction method based on the fixed number of times and the life prediction method based on the remaining ratio of spare blocks, which has been used to predict the life of flash memory.

• ETRI Journal
• /
• v.42 no.4
• /
• pp.505-517
• /
• 2020

The increasing size and complexity of deep neural networks (DNNs) necessitate the development of efficient high-performance accelerators. An efficient memory structure and operating scheme provide an intuitive solution for high-performance accelerators along with dataflow control. Furthermore, the processing of various neural networks (NNs) requires a flexible memory architecture, programmable control scheme, and automated optimizations. We first propose an efficient architecture with flexibility while operating at a high frequency despite the large memory and PE-array sizes. We then improve the efficiency and usability of our architecture by automating the optimization algorithm. The experimental results show that the architecture increases the data reuse; a diagonal write path improves the performance by 1.44× on average across a wide range of NNs. The automated optimizations significantly enhance the performance from 3.8× to 14.79× and further provide usability. Therefore, automating the optimization as well as designing an efficient architecture is critical to realizing high-performance DNN accelerators.

• Journal of Computing Science and Engineering
• /
• v.11 no.1
• /
• pp.1-8
• /
• 2017

Naive Bayes nearest neighbor (NBNN) is a simple image classifier based on identifying nearest neighbors. NBNN uses original image descriptors (e.g., SIFTs) without vector quantization for preserving the discriminative power of descriptors and has a powerful generalization characteristic. However, it has a distinct disadvantage. Its memory requirement can be prohibitively high while processing a large amount of data. To deal with this problem, we apply a spherical hashing binary code embedding technique, to compactly encode data without significantly losing classification accuracy. We also propose using an inverted index to identify nearest neighbors among binarized image descriptors. To demonstrate the benefits of our method, we apply our method to two existing NBNN techniques with an image dataset. By using 64 bit length, we are able to reduce memory 16 times with higher runtime performance and no significant loss of classification accuracy. This result is achieved by our compact encoding scheme for image descriptors without losing much information from original image descriptors.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.6 no.6
• /
• pp.383-391
• /
• 2011

As we know the effects of cache memory research, instruction and data caches can be separated for higher performance with Harvard CPUs. In this paper, we shows the efficiency of buffer system in the instruction and data flash storage medium. And we analyzed characteristics of the data and instruction flash and evaluated the performance. Finally, we propose the best buffer structure with an optimal block size and buffer size for the instruction and data flash.