• Journal of KIISE:Computer Systems and Theory
• /
• 제31권12호
• /
• pp.704-715
• /
• 2004

Recently, a single or multi processor system uses the hierarchical memory structure to reduce the time gap between processor clock rate and memory access time. A cache memory system includes especially two or three levels of caches to reduce this time gap. Moreover, one of the most important things In the hierarchical memory system is the hit rate in level 1 cache, because level 1 cache interfaces directly with the processor. Therefore, the high hit rate in level 1 cache is critical for system performance. A victim cache, another high level cache, is also important to assist level 1 cache by reducing the conflict miss in high level cache. In this paper, we propose the advanced high level cache management scheme based on the processor reuse information. This technique is a kind of cache replacement policy which uses the frequency of processor's memory accesses and makes the higher frequency address of the cache location reside longer in cache than the lower one. With this scheme, we simulate our policy using Augmint, the event-driven simulator, and analyze the simulation results. The simulation results show that the modified processor reuse information scheme(LIVMR) outperforms the level 1 with the simple victim cache(LIV), 6.7% in maximum and 0.5% in average, and performance benefits become larger as the number of processors increases.

• The KIPS Transactions:PartA
• /
• 제8A권4호
• /
• pp.319-330
• /
• 2001

In virtual memory system, when a process attempts to access a page that is not resident in memory, the system generates and handles a page fault that causes unpredictable delay. So virtual memory system is not appropriate for the real-time system, because it can increase the deadline miss ratio of real-time task. In multimedia system, virtual memory system may degrade the QoS(quality of service) of multimedia application. Furthermore, in general-purpose operating system, whenever a new task is dynamically loaded, virtual memory system suffers from extensive page fault that cause transient overloading state. In this paper, we present efficient overloading control mechanism called RBPFH (Rate-Based Page Fault Handling). A significant feature of the RBPFH algorithm is page fault dispersion that keeps page fault ratio from exceeding available bound by monitoring current system resources. Furthermore, whenever the amount of available system resource is changed, the RBPFH algorithm dynamically adjusts the page fault handling rate. The RBPFH algorithm is implemented in the Linux operating system and its performance measured. The results demonstrate RBPFH\`s superior performance in supporting multimedia applications. Experiment result shows that RBPFH could achieve 10%∼20% reduction in deadline miss ratio and 50%∼60% reduction in average delay.

• International journal of advanced smart convergence
• /
• 제3권2호
• /
• pp.18-21
• /
• 2014

A control application requirements currently used is very low, such as packet loss rate, minimum delay on sensor networks with quality of service (QoS) requirements some packet delivery guarantee. This paper is the sampling period at the end of the actuator and sensor data transfer related to the Miss ratio for each source sensor node, use the controller and the internal ANFIS. The proposed scheme has the advantages of simplicity, scalability, and General. Simulation results of the proposed scheme can provide QoS support in WSANs.

• ETRI Journal
• /
• 제36권1호
• /
• pp.179-182
• /
• 2014

This letter presents a very simple yet very effective solution for fast reference frame (RF) selection in H.264/AVC. By efficiently making use of the correlation between the best RF indices in various inter modes, the proposed method significantly reduces the number of RFs to be examined at the expense of a very small miss rate. Simulation results show that the proposed method not only improves upon the coding performance of conventional methods but also reduces the encoding time significantly.

• The Journal of the Acoustical Society of Korea
• /
• 제22권3E호
• /
• pp.124-132
• /
• 2003

We propose a new method for speech/non-speech classifiers based on concepts of the adaptive boosting (AdaBoost) algorithm in order to detect speech for robust speech recognition. The method uses a combination of simple base classifiers through the AdaBoost algorithm and a set of optimized speech features combined with spectral subtraction. The key benefits of this method are the simple implementation, low computational complexity and the avoidance of the over-fitting problem. We checked the validity of the method by comparing its performance with the speech/non-speech classifier used in a standard voice activity detector. For speech recognition purpose, additional performance improvements were achieved by the adoption of new features including speech band energies and MFCC-based spectral distortion. For the same false alarm rate, the method reduced 20-50% of miss errors.

• Journal of information and communication convergence engineering
• /
• 제10권1호
• /
• pp.78-84
• /
• 2012

This paper presents a branch prediction algorithm and a 4-way set-associative cache for performance improvement of an embedded RISC core and a clock-gating algorithm with observability don’t care (ODC) operation to reduce the power consumption of the core. The branch prediction algorithm has a structure using a branch target buffer (BTB) and 4-way set associative cache that has a lower miss rate than a direct-mapped cache. Pseudo-least recently used (LRU) policy is used for reducing the number of LRU bits. The clock-gating algorithm reduces dynamic power consumption. As a result of estimation of the performance and the dynamic power, the performance of the OpenRISC core applied to the proposed architecture is improved about 29% and the dynamic power of the core with the Chartered 0.18 ${\mu}m$ technology library is reduced by 16%.

• Proceedings of the IEEK Conference
• /
• 대한전자공학회 2006년도 하계종합학술대회
• /
• pp.853-854
• /
• 2006

Due to a recently developed approach to autopilot controller design for highly-maneuvering BTT (bank-to-turn) missiles, we now can derive explicitly the final-phase optimal guidance (OG) law considering the autopilot dynamics through direct use of the well-known linear optimal control theory. The proposed OG law can decrease the miss distance (MD) remarkably with small acceleration and roll rate profile at the time of interception.

• Proceedings of the Korean Information Science Society Conference
• /
• 한국정보과학회 2005년도 한국컴퓨터종합학술대회 논문집 Vol.32 No.1 (A)
• /
• pp.793-795
• /
• 2005

영속적인 데이터 저장이 가능한 차세대 비휘발성 메모리를 휘발성 메모리와 혼용하여 버퍼캐처로 사용하면, 안정성과 성능향상의 효과를 얻을 수 있다. 본 연구에서는 기존의 연구에서 제시한 캐처관리 정책을 시뮬레이터를 이용하여 실험하고 실험 결과를 분석하여 비휘발성 메모리가 추가된 캐처의 새로운 특성을 밝혀냈다. 비휘발성 메모리가 캐쉬에 포함되면 읽기 쓰기의 요청의 종류, 미스(miss)되었을 경우 캐쉬될 블록의 더티(dirty)여부, 읽기 요청이 적중(hit)되었을 때, 적중된 블록의 메모리 종류에 따라 각각의 요청을 처리하기 위한 디스크 접근횟수가 달라지는 특성을 나타낸다. 이 특성 때문에 비휘발성 메모리가 추가된 버퍼캐처는 적중률(hit rate) 보다는 디스크 접근횟수를 측정하는 것이 정확한 성능측정을 가능하게 한다.

• Journal of Biosystems Engineering
• /
• 제26권2호
• /
• pp.115-122
• /
• 2001

An impact-type seed-metering device was developed for the planting of rice-pellets. In this study, new design of pellet-metering device focused on simplicity and precision seeding for the planting of rice-seed pellets. In addition of seed-metering device, several devices were also developed such as seed-guiding device, seed-supplying tube and furrow opener for precision pellet planting. Field test was conducted to estimate the planting performance of the developed metering device. As a cam rotates, the impact bar of the metering device pushes a rice-seed pellet so that the seed can be discharged from the seed-supplying tube in the impact-type seed-metering device. Results of the tests showed that mean seeding spacing was 12cm at the traveling speed of 1.0m/s, corresponding to a target spacing for planting of rice-seed pellets. Also, both miss-seeded rate and damaged-seed rate were less than 2.0%, indicating acceptable levels for the precision planting. The developed mechanism of the impact-type metering device can be directly applied to the design of metering devices for the precision pellet planting of other crops.

• Ocean and Polar Research
• /
• 제23권4호
• /
• pp.379-388
• /
• 2001

Ch1 a abundance, Ch1 a-specific productivity and phytoplankton growth rate in each size fraction (pico, $<2{\mu}m$; nano, $2-10{\mu}m$; micro, > $10{\mu}m$) in the waters around the South Shetland Islands (Ant-arctic Peninsula Area) were analysed. Although Ch1 a-specific productivity and growth rate were highest in micro-size fractions, ChI a abundance was highest in pico-size fractions. Selective removal of nano- and micro-size phytoplankton especially by krill and salp grazing, but not limitation of phytoplankton growth, seemed to be the major reason to explain this miss match between productivity and abundance of the phytoplankton community.