The acceptance of NAND flash memories in the electronic world, due to its non-volatility, high density, low power consumption, small size and fast access speed is hopeful. Due to the limitations in life span and wear levelling, this memory needs special attention in its management techniques compared to the conventional techniques used in hard disks. In this paper, an efficient page replacement algorithm is proposed for NAND flash based memory systems. The proposed algorithm focuses on decision making policies based on the relative reference ratio of pages in memory. The size adjustable eviction window and the relative reference based shadow list management technique proposed by the algorithm contribute much to the efficiency in page replacement procedure. The simulation tool based experiments conducted shows that the proposed algorithm performs superior to the well-known flash based page replacement algorithms with regard to page hit ratio and memory read/write operations.
The non volatility, low power consumption and high density of NAND flash memories, made them an inevitable part of electronic industry. Due to the high wear out nature exhibited by flash systems, the algorithms used for page replacement in traditional memory systems are not suitable for flash page replacement. Along with the objective to maintain high hit rate, flash page replacement algorithms should aim at decreasing the page write count and maintain wear levelling. This paper presents major algorithms proposed for flash memory page replacement. The major contribution of this work is a relative study on various strategies, performance matrices and evaluation tools used for flash page replacement algorithm. The study shall help the researchers to identify the pros and cons of various flash page replacement algorithms, to identify the major gaps in between and to identify some commendable tools that can be used for flash page replacement algorithm evaluation. The gaps identified need to be addressed seriously in the near future.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.