• The Transactions of the Korea Information Processing Society
• /
• v.3 no.7
• /
• pp.1669-1679
• /
• 1996

In this paper, we address the problem of how to replace huffers in multimedia database systems with time-varying skewed data access. The access pattern in the multimedia database system to support audio-on-demand and video-on-demand services is generally skewed with a few popular objects. In addition the access pattem of the skewed objects has a time-varying property. In such situations, our analysis indicates that conventional LRU(least Recently Used) and LFU(Least Frequently Used) schemes for buffer replacement algorithm(ABRN:Adaptive Buffer Replacement using Neural suited. We propose a new buffer replacement algorithm(ABRN:Adaptive Buffer Replacement using Neural Networks)using a neural network for multimedia database systems with time-varying skewed data access. The major role of our neural network classifies multimedia objects into two classes:a hot set frequently accessed with great popularity and a cold set randomly accessed with low populsrity. For the classification, the inter-arrival time values of sample objects are employed to train the neural network.Our algorithm partitions buffers into two regions to combine the best roperties of LRU and LFU.One region, which contains the 핫셋 objects, is managed by LFU replacement and the other region , which contains the cold set objects , is managed by LRUreplacement.We performed simulation experiments in an actual environment with time-varying skewed data accsee to compare our algorithm to LRU, LFU, and LRU-k which is a variation of LRU. Simulation resuults indicate that our proposed algorthm provides better performance as compared to the other algorithms. Good performance of the neural network-based replacement scheme means that this new approach can be also suited as an alternative to the existing page replacement and prefetching algorithms in virtual memory systems.

• Journal of the Korea Society of Computer and Information
• /
• v.12 no.6
• /
• pp.139-146
• /
• 2007

A hard disk. which can be classified as an external storage is usually capacious and economical. In spite of the attractive characteristics and efforts on the performance improvement, however, the operation of the hard disk is apparently slower than a processor and the advancement has also been slowly conducted since it is based on mechanical process. On the other hand. the advancement of the processor has been drastically performed as semiconductor technology does. So, disk I/O sub-system becomes bottleneck of computer systems' performance. For this reason. the research on disk I/O sub-system is in progress to improve computer systems' performance. In this paper, we proposed multi-level LRU scheme and then apply it to the computer systems with buffer cache and disk cache. By applying the proposed scheme to computer systems. the average access time to ask blocks can be decreased. The efficiency of the proposed algorithm was verified by simulation results.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.2
• /
• pp.178-188
• /
• 2016

The traffic in the wired and wireless networks has increased exponentially because of increase of smart phone and improvement of PC performance. Multimedia services and file transmission such as Facebook, Youtube occupy a large part of the traffic. CDN is a technique that duplicates the contents on a remote web server of content provider to local CDN servers near clients and chooses the optimal CDN server for providing the content to the client in the event of a content request. In this paper, the content request message between CDN servers and the client used the SCRP algorithm utilizing the MST algorithm and the traffic throughput was optimized. The average response time for the content request is reduced by employing HC_LRU cache algorithm that improves the cache hit ratio. The proposed SCRP and HC_LRU algorithm may build a scalable content delivery network system that efficiently utilizes network resources, achieves traffic localization and prevents bottlenecks.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2006.05a
• /
• pp.81-84
• /
• 2006

유비쿼터스 컴퓨팅 환경으로 발전하면서 문자열 위주의 획일적 형태에서 음성, 이미지 등 다양한 형태의 데이터들을 처리하게 되었으며, 또한 빠르고 정확하게 처리되기를 요구하고 있다. 현재 데이터 처리 중심부에 있는 Database는 대부분이 Relation DB 위주로 되어 있어 Datafile 에 데이터를 저장하고 있어 대용량의 이미지 데이터 처리에 적합하지가 않다. 본 논문에서는 이러한 단점을 보강하기 위해 Relation DB 하에서 대용량의 이미지 데이터 처리를 가능하게 하는 기법을 제시한다. 이렇게 함으로써 이미지 데이터를 Upload, Download 시 따른 응답 속도를 보장 할 수 있도록 LRU 알고리즘 기반으로 제안을 하였다. 본 논문에서 제안된 기법은 시뮬레이션을 통해 (1)기존 RDB(Relational Database)의 BLOB(Binary Large Object)필드를 이용한 이미지 데이터 처리 방식, (2)별도의 저장 공간에 이미지 데이터를 입/출하는 방식, (3)별도의 저장 공간에 이미지 데이터를 입/출력할 때 LRU(least Recently Used)알고리즘을 이용하는 방식에 대하여 성능 평가를 하였다. 그 결과 (3)별도의 저장 공간에 LRU(least Recently Used)알고리즘을 이용하여 입/출력하는 방식이 (1)기존의 RDB(Relational Database)형태에 BLOB(binary large object)필드를 이용한 것 보다 성능이 높음을 확인하였다.

• Proceedings of the IEEK Conference
• /
• 1998.10a
• /
• pp.499-502
• /
• 1998

Most popular disk block replacement polices are LRU(Least Recently Used)policy and LFU(Least Frequently Used)policy. The LRU policy replaces blocks according to the most recent reference without considering the frequency of reference. The LFU policy replaces blocks according to the frequency of reference without considering the recently of the reference. In this thesis, a policy called LFR(least Frequently Use & Not Used Recently) disk block replacement policy is presented. The LFR policy subsumes the LFU policy and the NUR policy. The spectrum of the LFR policy exists between the LFU policy and the NUR policy because we co give different weight to each reference of a block. The implementation shows LFR policy outperforms the previously implemente LRU policy.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.04a
• /
• pp.445-447
• /
• 2000

인터넷이 급속도로 발전되면서 트래픽이 폭발적으로 증가하여 현재 라우터에 많은 부담을 주고 있다. 반면 스위칭 기술은 라우팅보다 빠르게 데이터를 전송할 수 있다. 그 결과 라우터 병목 현상을 해결하고자 IP 라우팅에 스위칭 기술을 접목한 레이블 스위칭 네트웍이 출현하게 되었다. 레이블 스위칭 기술 중 데이터 기반 레이블 스위칭에서 매우 중요한 것은 캐쉬 테이블 관리이다. 캐쉬 테이블에는 흐름 분류를 위한 정보와 레이블 스위칭을 위한 정보를 저장하고 있는데 캐쉬테이블 크기는 라우터 자원에 의해 제약을 받으므로 캐쉬 대체 기법이 필요하게 된다. 따라서 효율적인 캐쉬 테이블 관리를 위해 인터넷 트래픽 특성을 고려한 캐쉬 대체 기법에 관한 연구가 필요하다. 본 논문에서는 인터넷 트래픽 특성을 고려해 기본적인 FIFO, LFC, LRU 기법을 실제 인터넷 트래픽을 사용해 성능 평가하고 새로운 가중치 우선순위 LRU 기법을 제안한다. 특히 가중치 우선순위 LRU 기법은 플로우 인앤아웃 현상이 없고 시간이 지나도 새로운 플로우를 적절히 생성해내는 일관성을 지니면서도 스위칭 비용을 줄이는 장점을 가지고 있다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10c
• /
• pp.47-49
• /
• 2000

버퍼 캐쉬의 관리를 위해 많은 교체 정책들과 선반입 정책들이 연구되어져 왔다. 그러나, GNU/Linux를 포함한 많은 실제의 운영체제들은 일반적으로 Least Recently Used (LRU) 교체 정책을 사용한다. 본 논문에서는 끊임없이 적극적인 선반입이 이루어지는 가운데 버퍼관리와 선반입을 효율적으로 통합하는 SA-W2R 정책을 제안한다. 이 정책은 구현이 단순하여 실제 시스템에서 채택하기 용이하다. 이 정책은 기본적으로 버퍼 교체를 위하여 LRU 정책을 사용한다. 그러나 정책의 모듈성으로 인해 어떤 교체 정책도 이 정책에 적용될 수 있다. SA-W2R 정책에서는 선반입을 위해 오버헤드가 적어 일반적으로 많이 사용되는 LRU-One Block Lookahead(OBL) 정책을 사용한다. GNU/Linux 커널 버전 2.2.14에 구현된 SA-W2R 정책은 응용 프로그램의 실행 시간에 있어 현재 버전의 GNU/Linux 보다 최고 23%의 성능 향상을 보였다.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.4
• /
• pp.1-8
• /
• 2018

In this paper, we propose an adaptive partition cache replacement policy and evaluate the performance of our scheme using various monitoring ratios to help lifetime extension of non-volatile main memory systems without performance degradation. The proposal combines conventional LRU (Least Recently Used) replacement policy and Early Eviction Zone (E2Z), which considers a dirty bit as well as LRU bits to select a candidate block. In particular, this paper shows the performance of non-volatile memory using various monitoring ratios and determines optimized monitoring ratio and partition size of E2Z for reducing the number of writebacks using cache hit counter logic and hit predictor. In the experiment evaluation, we showed that 1:128 combination provided the best results of writebacks and runtime, in terms of performance and complexity trade-off relation, and our proposal yielded up to 42% reduction of writebacks, compared with others.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.46 no.1
• /
• pp.68-75
• /
• 2009

As the recent performance of microprocessor is improving quickly, the necessity of cache is growing because of the increase of the access time of main memory. Every block of direct-mapped cache maps to one cache line. Although the mapping rule is simple, if different blocks map to one cache line, the miss ratio will be higher than the set-associative cache due to conflicts. In this paper, for the improvement of the direct-mapped cache of OpenRISC, 4-way set-associative cache is proposed. Four blocks of the main memory of the proposed cache map to one cache line so that the miss ratio is less than the direct-mapped cache. Pseudo-LRU Policy, which is one of the Line Replacement Policies, is used for decreasing the number of bits that store LRU value. The OpenRISC core including the 4-way set-associative cache was verified with FPGA emulation. As the result of performance measurement using test program, the performance of the OpenRISC core including the 4-way set-associative cache is higher than the previous one by 50% and the decrease of miss ratio is more than 15%.

• The KIPS Transactions:PartD
• /
• v.12D no.2 s.98
• /
• pp.283-288
• /
• 2005

Test case prioritization methods schedule test cases for execution when we can not practically run all test cases for regression testing. We proposed a new prioritization method that is based on historical execution and mr detection data. And we conducted an experiment to compare the proposed method with existing Random and LRU methods using the fault age under the long run environment as criterion. The experiment shows several interesting results. First, our results show that they are complementary. Random method shows good performance for programs that have many error-detectable test cases and HED is more effective for the programs that can be detected by very small amount of test cases. But LRU is more effective for the programs that have relatively medium amount of error detectable test cases. Next, the performance of prioritization method is affected by the size of test suites. Two experiments that have different size of test suites show considerably different fault ages and performance order. And lastly, the $20\%$ of test cases shows considerably good performance compared to the execution result of the full test suite.