• Journal of KIISE:Software and Applications
• /
• v.32 no.10
• /
• pp.1003-1012
• /
• 2005

The most significant difference of embedded systems from general purpose systems is that embedded systems are allowed to use only limited resources including battery and memory. Especially, the number of applications increases which deal with multimedia data. In those systems with high data computations, the delay of memory access is one of the major bottlenecks hurting the system performance. As a result, many researchers have investigated various techniques to reduce the memory access cost. Most programs generally have locality in memory references. Temporal locality of references means that a resource accessed at one point will be used again in the near future. Spatial locality of references is that likelihood of using a resource gets higher if resources near it were just accessed. The latest embedded processors usually adapt cache memory to exploit these two types of localities. Processors access faster cache memory than off-chip memory, reducing the latency. In this paper we will propose the enhanced dynamic allocation technique for structure-type data in order to eliminate unused memory space and to reduce both the cache miss rate and the application execution time. The proposed approach aggregates fields from multiple records dynamically allocated and consecutively remaps them on the memory space. Experiments on Olden benchmarks show $13.9\%$ L1 cache miss rate drop and $15.9\%$ L2 cache miss drop on average, compared to the previously proposed techniques. We also find execution time reduced by $10.9\%$ on average, compared to the previous work.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.3
• /
• pp.41-49
• /
• 2009

Flash memory has become increasingly requestion for the importance and the demand as a storage due to its low power consumption, cheap prices and large capacity medium. This research is to design a high performance flash memory structure for the substitution of a hard-disk by dynamic prefetching of aggressive spatial locality from the spatial smart buffer system. The proposed buffer system in a NAND flash memory consists of three parts, i.e., a fully associative victim buffer for temporal locality, a fully associative spatial buffer for spatial locality, and a dynamic fetching unit. We proposed new dynamic prefetching algorithm for aggressive spatial locality. That is to use the flash memory instead of the hard disk, the proposed flash system can achieve better performance gain by overcoming many drawbacks of the flash memory by the new structure and the new algorithm. According to the simulation results, compared with the smart buffer system, the average miss ratio is reduced about 26% for Mediabench applications. The average memory access times are improved about 35% for Mediabench applications, over 30% for Spec2000 applications.

• Journal of KIISE:Computer Systems and Theory
• /
• v.27 no.11
• /
• pp.908-918
• /
• 2000

캐쉬의 성능을 향상시키는 가장 효과적인 방법은 프로그램 수행 특성에 내재되어 있는 시간적 (temporal locality) -공간적 지역성 (spatial locality)을 활용하는 것이다. 본 논문에서는 추가적인 장치나 컴파일러의 도움 없이 단지 캐쉬의 구조적인 특징과 간단한 메커니즘만을 이용하여 두 가지 타입의 지역성을 효과적으로 반영할 수 있는 새로운 캐쉬 시스템이 제안된다. 제안하는 새로운 캐쉬 시스템은 다른 블록 크기와 다른 연관도를 가지는 두 개의 캐쉬로써 구성되어 진다. 즉 작은 블록 크기를 지원하는 직접사상 캐쉬 (direct-mapped cache)와 큰 블록을 지원하는 완전 연관 버퍼 (fully-associative buffer)로 구성되어 진다. 큰 블록은 여러 개의 작은 블록으로 구성되어지며 두 캐쉬에서 접근 실패가 발생할 경우 직접사상 캐쉬의 접근 실패가 발생한 작은 블록과 그 이웃 작은 블록을 완전 연관 버퍼에 저장시킴으로써 한번 참조가 일어난 블록의 이웃 블록이 참조될 확률이 높다는 공간적 지역성의 특성을 효과적으로 반영할 수 있다. 또한 참조가 일어난 블록은 제어 비트를 사용하여 선택적으로 작은 블록을 직접사상 캐쉬에 저장함으로써 시간적 지역성을 보다 효과적으로 사용할 수 있다 시뮬레이션 결과에 따르면 기존의 직접사상 캐쉬의 4배 크기보다도 좋은 성능 향상을 보이고 있으며, 동일한 크기의 victim 캐쉬보다 우수한 성능을 보이고 소비 전력 면에서는 5% 정도의 전력 감소를 보이고 있다.

• 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.

• Journal of information and communication convergence engineering
• /
• v.12 no.3
• /
• pp.161-167
• /
• 2014

Web caches help to reduce latencies arising from slow networks through storing and reusing what was used before. Repeat access to a cached resource does not incur network latencies. However, resources that have never been used will not be found in the cache. Cache prefetching is a technique that helps to fill a cache with still-unused resources in anticipation that these resources will be used in the near future. Typically these unused resources are related to the resources that have been accessed in the recent past. While web caching exploits temporal locality, prefetching attempts to exploit spatial locality. Access to the prefetched resources will be cache hits, and therefore reduces the latency as perceived by the user. This paper reviews the cache infrastructure supported by the hypertext transfer protocol and discusses web cache prefetching in general, including Mozilla's prefetching infrastructure. It then classifies and reviews some prefetching techniques.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.04b
• /
• pp.4-6
• /
• 2001

데이터베이스 관리시스템에서 데이터를 디스크에서 읽어오는 작업은 많은 비용을 필요로 한다. 따라서 시스템의 성능을 향상시키기 위해서는 I/O의 횟수를 최소화는 것이 가장 중요한 문제이다. 특히 공간데이터베이스 환경에서는 클라이언트 버퍼의 크기가 데이터베이스의 크기에 비해 매우 작기 때문에 버퍼를 효율적으로 사용하여 I/O 회수를 줄이는 문제는 더욱 중요하게 고려하여야 한다. 지금까지 디스크 I/O 횟수를 줄이기 위해서 많은 버퍼관리 기법들이 제안되었지만, 그 기법들은 시간적 근접성만을 고려해왔기 때문에 공간적 근접성도 존재하는 공간데이터베이스 환경에서는 최적의 성능을 보여주지 못했다. 본 논문에서는 공간 데이터베이스의 시간적 근접성과 공간적 근접성을 동시에 고려하는 새로운 버퍼관리기법인 SLM-tree Buffer Management Strategy를 제안한다. 제안한 버퍼관리기법은 공간 데이터베이스 환경에서 디스크 I/O의 횟수를 현저하게 줄임으로서 기존의 방법들에 비해 월등한 성능을 보여준다.

• Journal of Ubiquitous Convergence Technology
• /
• v.1 no.1
• /
• pp.28-34
• /
• 2007

Tree-based reliable multicast protocols provide scalability by distributing error-recovery tasks among several repair nodes. These repair nodes perform local error recovery for their receiver nodes using the data stored in their buffers. We propose a packet loss patterns adaptive feedback scheduling scheme to manage these buffers in an efficient manner. Under our scheme, receiver nodes send NAKs to repair nodes to request packet retransmissions only when the packet losses are independent events from other nodes. At dynamic and infrequent intervals, they also send ACKs to indicate which packets can be safely discarded from the repair node's buffer. Our scheme reduces delay in error recovery because the requested packets are almost always available in the repair node's buffers. It also reduces the repair node's workload because (a) each receiver node sends infrequent ACKs with non-fixed intervals and (b) their sending times are fairly distributed among all the receiver nodes.

• Atmosphere
• /
• v.24 no.2
• /
• pp.159-171
• /
• 2014

This study investigated the temporal and spatial characteristics of summertime (June-August) precipitation over Korean peninsula, using Korea Meteorological Administration (KMA)is Automated Synoptic Observing System (ASOS) data for the period of 1973-2010 and Automatic Weather System (AWS) data for the period of 1998-2010.The authors looked through climatological features of the summertime precipitation, then examined the degree of locality of the precipitation, and probable precipitation amount and its return period of 100 years (i.e., an extreme precipitation event). The amount of monthly total precipitation showed increasing trends for all the summer months during the investigated 38-year period. In particular, the increasing trends were more significant for the months of July and August. The increasing trend of July was seen to be more attributable to the increase of precipitation intensity than that of frequency, while the increasing trend of August was seen to be played more importantly by the increase of the precipitation frequency. The e-folding distance, which is calculated using the correlation of the precipitation at the reference station with those at all other stations, revealed that it is August that has the highest locality of hourly precipitation, indicating higher potential of localized heavy rainfall in August compared to other summer months. More localized precipitation was observed over the western parts of the Korean peninsula where terrain is relatively smooth. Using the 38-years long series of maximum daily and hourly precipitation as input for FARD2006 (Frequency Analysis of Rainfall Data Program 2006), it was revealed that precipitation events with either 360 mm $day^{-1}$ or 80 mm $h^{-1}$ can occur with the return period of 100 years over the Korean Peninsula.

• Journal of KIISE:Computer Systems and Theory
• /
• v.29 no.6
• /
• pp.346-353
• /
• 2002

The explosive increase of World Wide Web usage has incurred significant amount of network traffic and server load. To overcome these problems, web proxy caching replicates frequently requested documents in the web proxy closer to the users. Cache utilization depends on the replacement policy which tries to store frequently requested documents in near future. Temporal locality and Zipf frequency distribution, which are commonly observed in web proxy workloads, are considered as the important properties to predict the popularity of documents. In this paper, we propose a novel cache replacement policy, called Adaptive LFU (ALFU), which incorporates 1) Zipf frequency distribution by utilizing LFU and 2) temporal locality adaptively by measuring the amount of the popularity reduction of documents as time passed efficiently. We evaluate the performance of ALFU by comparing it to other policies via trace-driven simulation. Experimental results show that ALFU outperforms other policies.

• The KIPS Transactions:PartA
• /
• v.11A no.1
• /
• pp.11-20
• /
• 2004

Multimedia data processing in streaming pattern contains high spatial locality and low temporal locality. This paper has proposed a dynamic data prefetching scheme that fully exploits the regularity between memory addresses referred consecutively. Compared to the existing data Prefetching scheme, the Proposed scheme can reduce data Prefetching error when an application divides an way into smaller blocks and processes them block by block. Experimental results on various media benchmark programs show the proposed scheme predicts memory addresses more accurately and results in better performance than existing prefetching schemes.