• Journal of the Korea Society of Computer and Information
• /
• v.16 no.2
• /
• pp.1-8
• /
• 2011

NAND type Flash memory has performing much researches for a hard disk substitution due to its low power consumption, cheap prices and a large storage. Especially, the NAND type flash memory is using general buffer systems of a cache memory for improving overall system performance, but this has shown a tendency to emphasize in terms of data. So, our research is to design a high performance instruction NAND type flash memory structure by using a buffer system. The proposed buffer system in a NAND flash memory consists of two parts, i.e., a fully associative temporal buffer for branch instruction and a fully associative spatial buffer for spatial locality. The spatial buffer with a large fetching size turns out to be effective serial instructions, and the temporal buffer with a small fetching size can achieve effective branch instructions. According to the simulation results, we can reduce average miss ratios by around 77% and the average memory access time can achieve a similar performance compared with the 2-way, victim and fully associative buffer with two or four sizes.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.12 no.4
• /
• pp.193-204
• /
• 2017

Various 3D-stacked DRAMs have been proposed to overcome the memory wall problem. Hybrid Memory Cube (HMC) is a true 3D-stacked DRAM with stacked DRAM layers on top of a logic layer. The logic die is mainly used to implement a memory controller for HMC, and it is connected through a high speed serial link called SerDes with a host that is either a processor or another HMC. In HMC, the serial link is crucial for both performance and power consumption. Therefore, it is important that the link is configured properly so that the required performance should be satisfied while the power consumption is minimized. In this paper, we propose a HMC system model included the high speed serial link to estimate performance accurately. Since the link modeling strictly follows the link flow control mechanism defined in the HMC spec, the actual HMC performance can be estimated accurately with respect to each link configuration. Various simulations are conducted in order to deduce the correlation between the HMC performance and the link configuration with regard to memory utilization. It is confirmed that there is a strong correlation between the achievable maximum performance of HMC and the link configuration in terms of both bandwidth and latency. Therefore, it is possible to find the best link configuration when the required HMC performance is known in advance, and finding the best configuration will lead to significant power saving while the performance requirement is satisfied.

• Smart Media Journal
• /
• v.4 no.4
• /
• pp.56-63
• /
• 2015

Modern GPU can execute mass parallel computation by exploiting many GPU core. GPGPU architecture, which is one of approaches exploiting outstanding computational resources on GPU, executes general-purpose applications as well as graphics applications, effectively. In this paper, we investigate the impact of memory-efficiency and performance according to number of CTAs(Cooperative Thread Array) on a SM(Streaming Multiprocessors), since the analysis of relation between number of CTA on a SM and them provides inspiration for researchers who study the GPU to improve the performance. Our simulation results show that almost benchmarks increasing the number of CTAs on a SM improve the performance. On the other hand, some benchmarks cannot provide performance improvement. This is because the number of CTAs generated from same kernel is a little or the number of CTAs executed simultaneously is not enough. To precisely classify the analysis of performance according to number of CTA on a SM, we also analyze the relations between performance and memory stall, dram stall due to the interconnect congestion, pipeline stall at the memory stage. We expect that our analysis results help the study to improve the parallelism and memory-efficiency on GPGPU architecture.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.1
• /
• pp.108-114
• /
• 2004

In this paper we propose the boot system using CF memory card and study the system implementation method. The system that is proposed in this paper basically consist of high performance microprocessor, small amount of program memory and CF memory card. And added LCD module and touch panel for the user interface. This system use the CF memory card and DRAM instead of the Flash memory, so it can reduce the system cost. And system performance is increased because of the system program running in the DRAM.

• Journal of Korea Multimedia Society
• /
• v.2 no.4
• /
• pp.367-377
• /
• 1999

Nowadays, the number of database applications which need fast transaction processing are increasing. One way to improve the performance of transaction processing is to reside the whole database in main memory As semiconductor memory becomes cheaper and chip densities increase, the research to improve transaction throughput rates of transaction processing system, using main memory databases, has begun In this thesis, how to implement a high performance transaction processing system based on main memory databases, new concurrency control scheme, recovery scheme and storage structure is presented. The objective of the proposed schemes is to improve the transaction processing system performance measured by transaction throughput and response times.

• Research in Mathematical Education
• /
• v.13 no.3
• /
• pp.181-195
• /
• 2009

Students' approaches to mathematical problem solving vary greatly with each other. The main objective of the current study was to compare students' performance with different thinking styles (divergent vs. convergent) and working memory capacity upon mathematical problem solving. A sample of 150 high school girls, ages 15 to 16, was studied based on Hudson's test and Digit Span Backwards test as well as a math exam. The results indicated that the effect of thinking styles and working memory on students' performance in problem solving was significant. Moreover, students with divergent thinking style and high working memory capacity showed higher performance than ones with convergent thinking style. The implications of these results on math teaching and problem solving emphasizes that cognitive predictor variable (Convergent/Divergent) and working memory, in particular could be challenging and a rather distinctive factor for students.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.12-15
• /
• 2020

Data access characteristics can directly affect the efficiency of the system execution. This research is to design an accurate predictor by using historical memory access information, where highly accessible data can be migrated from low-speed storage (SSD/HHD) to high-speed memory (Memory/CPU Cache) in advance, thereby reducing data access latency and further improving overall performance. For this goal, we design a locally weighted linear regression prefetch scheme to cope with irregular access patterns in large graph processing applications for a DARM-PCM hybrid memory structure. By analyzing the testing result, the appropriate structural parameters can be selected, which greatly improves the cache prefetching performance, resulting in overall performance improvement.

• Journal of Korea Multimedia Society
• /
• v.12 no.2
• /
• pp.165-177
• /
• 2009

Embedded database systems (EDBMS) based on NAND flash memories are widely adopted for logging data on sensor nodes. Since write and erase operations of a flash memory are time consuming compared to read operations and wear memory cells, it is important to reduce these operations to enhance the EDBMS performance and to extend the memory life. In this paper, we propose a delayed write scheme to archive this goal. Proposed scheme stores updated parts of database pages into delayed write records to reduce the database page writes. By doing that, it decreases write and erase operations on a flash memory. Therefore, the proposed scheme enhances the logging performance of a write-intensive EDBMS on a sensor node and extends the flash memory life.

• Journal of electromagnetic engineering and science
• /
• v.9 no.2
• /
• pp.71-77
• /
• 2009

OFDM(Orthogonal Frequency Division Multiplexing) signals sutler serious nonlinear distortion in the nonlinear HPA(High Power Amplifier) because of high PAPR(Peak Average Power Ratio). Nonlinear distortion can be improved by a pre-distorter, but this pre-distorter is insufficient when the PAPR is very high in an OPFDM system. In this paper, a DFT(Discrete Fourier Transform) transform technique is introduced for PAPR reduction. It is especially important to consider the memory effect of HPA for more precise predistortion. Therefore, in this paper, we consider two models, the TWTA(Traveling-Wave Tube Amplifier) model of Saleh without a memory effect and the HPA memory polynomial model that has a memory effect. We design a pre-distorter and an adaptive pre-distorter that uses the NLMS(Normalized Least Mean Square) algorithm for the compensation of this nonlinear distortion. Without the consideration of a memory effect, the system performance would be degraded, even if the pre-distorter is used for the compensation of the nonlinear distortion. From the simulation results, we can confirm that the proposed system shows an improvement in performance.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.5 no.5
• /
• pp.389-394
• /
• 2004

In this paper, according to characteristics of flash memory, a memory recycling method is proposed in order to decrease the necessary cost preventing performance degradation at the same time, In order to optimize the demanding costs, the new approach partitions the search space of flash memory segments into K segment groups, A method for memory space allocation, in addition, is proposed in order to satisfy the goal of even wearing over the total memory space, The optimized configuration of the proposed method is achieved through experiments, The fact that the newly proposed methods outperform the existing approaches regarding cost and performance is evaluated by simulations, Furthermore the experimental results demonstrate that the memory allocation method affects even wearing in great deal.