• Journal of the Semiconductor & Display Technology
• /
• v.21 no.3
• /
• pp.1-6
• /
• 2022

Modern computer systems usually have special hardware for operations used in deep learning workload even edge computing environment. Non-volatile memories (NVMs) have been considered for alternative memory storage because they consume little static energy and occupy small area. However, there is a problem for NVMs to be directly adopted. An NVM cell has limited write endurance, so that the lifetime of NVM-based memory system is much shorter than that of conventional memory system. To overcome this problem for the deep learning system, this paper proposes a novel method to extend the lifetime based on the analysis of the deep learning workloads. If an incoming block has more than a predefined number of frequently used values, the cacheline is defined as write friendly block. During the victim selection, the cacheline has lower possibility to be chosen as victim. The experimental results show that the lifetime is increased by about 50% and energy consumption is decreased by 3% with a little performance hurt.

• Spatial Information Research
• /
• v.11 no.3
• /
• pp.261-274
• /
• 2003

The effective probability-based tile pre-fetching algorithm and the collaborative cache replacement algorithm are able to reduce the response time for user's requests by transferring tiles which will be used in advance and determining tiles which should be removed from the restrictive cache space of a client based on the future access probabilities in Web GISs(Geographical Information Systems). The Web GISs have multi-level abstracted data for the quick response time when zoom-in and zoom-out queries are requested. But, the previous pre-fetching algorithm is applied on only two-dimensional pre-fetching space, and doesn't consider expanded pre-fetching space for multi-level abstracted data in Web GISs. In this thesis, a probability-based pre-fetching algorithm for multi-level abstracted in Web GISs was proposed. This algorithm expanded the previous two-dimensional pre-fetching space into three-dimensional one for pre-fetching tiles of the upper levels or lower levels. Moreover, we evaluated the effect of the proposed pre-fetching algorithm by using a simulation method. Through the experimental results, the response time for user requests was improved 1.8%∼21.6% on the average. Consequently, in Web GISs with multi-level abstracted data, the proposed pre-fetching algorithm and the collaborative cache replacement algorithm can reduce the response time for user requests substantially.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.4
• /
• pp.117-123
• /
• 2013

In the recent cloud storage environment, the amount of SSD (Solid-State Drive) replacing with the traditional hard disk drive is increasing. Management of SSD for its space efficiency has become important since SSD provides fast IO performance due to no mechanical movement whereas it has wearable characteristics and does not provide in place update. In order to manage space efficiency of SSD, data de-duplication technique is frequently used. However, this technique occurs much overhead because it consists of data chunking, hasing and hash matching operations. In this paper, we propose new data de-duplication method using PRAM cache. The proposed method uses hierarchical hash tables and LRU(Least Recently Used) for data replacement in PRAM. First hash table in DRAM is used to store hash values of data cached in the PRAM and second hash table in PRAM is used to store hash values of data in SSD storage. The method also enhance data reliability against power failure by maintaining backup of first hash table into PRAM. Experimental results show that average writing frequency and operation time of the proposed method are 44.2% and 38.8% less than those of existing data de-depulication method, respectively, when three workloads are used.

• Convergence Security Journal
• /
• v.6 no.4
• /
• pp.91-99
• /
• 2006

Generally, a study of web caching is conducted on a performance improvement with structural approaches and a new hybrid method using existing methods, and studies on caching method itself. And existing analysis of reference-characteristic are conducted on a history analysis and a preference of users, a view point of data mining by log analysis. In this study, we analyze the reference-characteristic of web object on a view point of a characteristic of probability-distribution and a mean value of lifetime of a web-object. And using this result, we propose the new method for a performance improvement of a web-caching.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.1
• /
• pp.1-10
• /
• 2010

Recently heterogeneous storage system such as hybrid hard disk drive (H-HDD) combining flash memory and magnetic disk is launched, according as the read performance of NAND flash memory is enhanced as similar to that of hard disk drive (HDD) and the power consumption of NAND flash memory is reduced less than that of HDD. However, the read and write operations of NAND flash memory are slower than those of rotational disk. Besides, serious overheads are incurred on CPU and main memory in the case that intensive write requests to flash memory are repeatedly occurred. In this paper, we propose the Least Frequently Used-Hot scheme that replaces the data blocks whose reference frequency of read operation is low and update frequency of write operation is high, and the data flushing scheme that rearranges the data blocks into the multi-zone of the rotation disk. Experimental results show that the execution time of the proposed method is 38% faster than those of conventional LRU and LFU block replacement schemes in I/O performance aspect and the proposed method increases the life span of Non-Volatile Cache 40% higher than those of conventional LRU, LFU, FIFO block replacement schemes.

• Journal of Internet Computing and Services
• /
• v.12 no.2
• /
• pp.37-46
• /
• 2011

The importance of data service with mobile is becoming more and more significant with the development of wireless network. However, due to the several type of mobile devices and contents, there is a problem that mobile contents should be edited according to the features of the mobile devices and the service providers. Fortunately, there is some solutions that convert mobile contents automatically according to mobile operator. Nevertheless, it has some issues that the response time of content service is delayed when converting mobile contents in real-time. In this paper, we propose an image cache replacement algorithm for minizing the volume of the real-time image transformation. Also, using both of the pre-conversion method and the real-time conversion method to improve storage space and response time.