• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06a
• /
• pp.143-145
• /
• 2012

멀티레벨 스토리지 접근은 클라우드 시스템, 가상화 환경, 네트워크 기반 스토리지 등 많은 컴퓨팅 환경에서 널리 사용되고 있다. 이러한 멀티레벨 스토리지의 접근성능을 향상시키려면, 되도록 하위 레벨의 스토리지로 요청이 일어나지 않게 하는 것이 중요하며, 이는 각 레벨의 버퍼캐시 성능이 큰 영향을 미친다. 다양한 버퍼캐시 알고리즘들 중 ARC 알고리즘은 동작의 간결성과 고성능으로 인해, 많은 워크로드에서 가장 좋은 성능을 보이는 캐시 알고리즘으로 알려져 있다. 그러나, ARC 알고리즘은 2차 레벨 버퍼캐시에서는 좋은 성능을 보이지 않는데, 이는 ARC 알고리즘이 멀티레벨 캐시의 특성을 반영하지 못하고 있기 때문이다. 본 논문에서는 멀티레벨 캐시의 특성과 이를 반영한 M-ARC 라는 멀티레벨 버퍼캐시 알고리즘을 제안한다. 제안하는 알로리즘은 기존 ARC에 비해 약 2배 이상 향상된 성능을 보여주고 있다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10c
• /
• pp.421-423
• /
• 2002

동영상 정보 검색 시스템은 비교적 작은 크기의 동영상 클립과 클립을 인덱싱하기 위한 키 프레임으로 구성된다. 본 논문에서는 동영상 정보 검색 시스템을 위한 버퍼 캐시에서 버퍼 교체 기법을 연구하였고, 버퍼 캐시 사용의 효율성을 연구하였다. 실험을 통해 버퍼 캐시가 좋은 성능을 가지려면 적은 수의 동영상 클립에 요청이 편중되어야 함을 알 수 있었다.

• 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.

• The Journal of the Korea Contents Association
• /
• v.4 no.3
• /
• pp.71-80
• /
• 2004

In distributed file-systems, cooperative caching algorithm which owns the data cached at each node jointly is used to reduce an expense of disk access. Cooperative caching algorithm is the method that increases a cache hit-ratio and decrease a disk access as it holds the cache information of distributed systems in common and makes cache larger virtually. Recently, several cooperative caching algorithms decrease the message costs by using approximate information of the cache and increase the cache hit-ratio by using local and global cache fields dynamically. And they have an advantage that increases the whole field hit-ratio by sending a replaced buffer to the idle node on buffers replacement in order to maintain the replaced cache in the cache field. However the wrong approximate information deteriorates the performance, the consistency maintenance goes to great expense to exchange messages and the cost that manages Age-information of each node to choose the idle node increases. In this thesis, we propose a cooperative cache algorithm that maintains correct cache information, minimizes the maintenance cost for consistency and the management cost for buffer Age-information. Also, we show the superiority of our algorithm through the performance evaluation.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.1
• /
• pp.14-20
• /
• 2009

Recently, NAND flash memory is used not only for portable devices, but also for personal computers and server computers. Buffer cache replacement policies for the hard disks such as LRU and LFU are not good for NAND flash memories because they do not consider about the characteristics of NAND flash memory. CFLRU and its variants, CFLRU/C, CFLRU/E and DL-CFLRU/E(CFLRUs) are the buffer cache replacement policies considered about the characteristics of NAND flash memories, but their performances are not better than those of LRD. In this paper, we propose a new buffer cache replacement policy for NAND flash memory. Which is based on LFU and is taking into account the characteristics of NAND flash memory. And we estimate the performance of hit ratio and flush operation numbers. The proposed policy shows better hit ratio and the number of flush operation than any other policies.

• The KIPS Transactions:PartA
• /
• v.9A no.2
• /
• pp.163-170
• /
• 2002

Previous buffer cache schemes for continuous media file system only exploited the sequentiality of continuous media accesses and didn't consider looping references. However, in some video applications like foreign language learning, users mark the scene as loop area and then application automatically playbacks the scene several times. In this paper, we propose a novel buffer cache scheme for continuous media file system that sequential and looping references exist together. Proposed scheme increases the cache hit ratio by detecting reference pattern of files and appling an appropriate replacement policy to each file.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.7
• /
• pp.9-16
• /
• 2022

Today, with the advent of the 4th industrial revolution, IoT (Internet of Things) systems are advancing rapidly. For this reason, a various application with high-performance and large-capacity are emerging. Therefore, there is a need for low-power and high-performance memory for computing systems with these applications. In this paper, we propose an effective structure for the L1 cache memory, which consumes the most energy in the computing system. The proposed cache system is largely composed of two parts, the L1 main cache and the buffer cache. The main cache is 2 banks, and each bank consists of a 2-way set association. When the L1 cache hits, the data is copied into buffer cache according to the proposed algorithm. According to simulation, the proposed L1 cache system improved the performance of energy delay products by about 65% compared to the existing 4-way set associative cache memory.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.2
• /
• pp.1-8
• /
• 2013

TIn this paper, we propose a high performance L1 cache structure on the high clock CPU of 4GHz. The proposed cache memory consists of three parts, i.e., a direct-mapped cache to support fast access time, a two-way set associative buffer to exploit temporal locality, and a buffer-select table. The most recently accessed data is stored in the direct-mapped cache. If a data has a high probability of a repeated reference, when the data is replaced from the direct-mapped cache, the data is selectively stored into the two-way set associative buffer. For the high performance and low power consumption, we propose an one way among two ways set associative buffer is selectively accessed based on the buffer-select table(BST). According to simulation results, Energy $^*$ Delay product can improve about 45%, 70% and 75% compared with a direct mapped cache, a four-way set associative cache, and a victim cache with two times more space respectively.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.9
• /
• pp.11-19
• /
• 2013

Most modern computer systems employ cache systems in order to alleviate the access time gap between processor and memory system. The power dissipated by the cache systems becomes a significant part of the total power dissipated by whole microprocessor chip. Therefore, power reduction in the cache system becomes one of the important issues. Partial tag cache is the system for the least power consumption. The main power reduction for this method is due to the use of small partial tag matching, not full tag matching. In this paper, we first analyze the previous regular partial tag cache systems and propose a new address matching mechanism by using locality buffer and address compression. In simulation results, the proposed model shows 18% power reduction in average, still providing same performance level, compared to regular cache.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07a
• /
• pp.766-768
• /
• 2005

컴퓨팅 환경이 무선과 휴대용 시스템으로 변화하면서, 전력효율이 점점 중요해지고 있다. 특히 내장형 시스템일 경우에 더욱 그러한데 이중 메모리에서 소모되는 전력이 전체 전력소모의 두 번째 큰 요소가 되고 있다. 메모리 시스템에서의 전력소모를 줄이기 위해서 DRAM의 저전력 모드인 냅모드(nap mode)를 활용할 수 있다. 냅모드는 액티브 모드(active mode)일 때의 $28\%$의 전력만을 소모한다. 하지만 하드웨어 컨트롤러는 운영체제가 협조하지 않으면 이 기능을 효율적으로 활용하지 못한다. 이 논문에서는 DRAM의 액티브 유닛(active unit)의 수를 최소화하는 방법에 초점을 맞춘다. 운영체제는 참조되지 않는 메모리를 냅모드에 놓음으로써 최소한의 유닛들만을 액티브 모드에 놓아 프로그램이 수행될 수 있도록 피지컬(physical) 페이지들을 할당한다. 이것은 PAVM(Power Aware Virtual Memory) 연구의 일반화된 시스템 전반에 대한 연구라고 할 수 있다. 우리는 모든 피지컬 메모리를 고려하고 있으며, 특히 평균적으로 전체 메모리의 절반을 사용하는 버퍼 캐시를 고려하고 있다. 버퍼 캐시의 용량과 그 중요성 때문에 PAVM 방식은 버퍼 캐시를 고려하지 않고는 완전한 해법이 되지 못한다. 이 논문에서 우리는 메모리의 사용처를 분석하고 저전력 페이지 할당 정책을 제안한다. 특히 프로세스의 주소공간에 매핑(mapping)된 페이지들과 버퍼 캐시가 고려된다. 이 두 종류의 페이지들간의 상호작용과 그 관계를 분석하고 저전력을 위해 이러한 관계를 이용한다.