Amortized efficiency of list update and paging rules
Communications of the ACM
Journal of Algorithms
Online computation and competitive analysis
Online computation and competitive analysis
Competitive analysis of randomized paging algorithms
Theoretical Computer Science
An efficient R-tree implementation over flash-memory storage systems
GIS '03 Proceedings of the 11th ACM international symposium on Advances in geographic information systems
Algorithms and data structures for flash memories
ACM Computing Surveys (CSUR)
An efficient B-tree layer implementation for flash-memory storage systems
ACM Transactions on Embedded Computing Systems (TECS)
ESA '08 Proceedings of the 16th annual European symposium on Algorithms
ICDE '09 Proceedings of the 2009 IEEE International Conference on Data Engineering
On Computational Models for Flash Memory Devices
SEA '09 Proceedings of the 8th International Symposium on Experimental Algorithms
A study of replacement algorithms for a virtual-storage computer
IBM Systems Journal
Characterizing the performance of flash memory storage devices and its impact on algorithm design
WEA'08 Proceedings of the 7th international conference on Experimental algorithms
| Hi-index | 0.00 |
We propose a variation of online paging in two-level memory systems where pages in the fast cache get modified and therefore have to be explicitly written back to the slow memory upon evictions. For increased performance, up to 驴 arbitrary pages can be moved from the cache to the slow memory within a single joint eviction, whereas fetching pages from the slow memory is still performed on a one-by-one basis. The main objective in this new 驴-paging scenario is to bound the number of evictions. After providing experimental evidence that 驴-paging can improve the performance of flash-memory devices in the context of translation layers we turn to the theoretical connections between 驴-paging and standard paging. We give lower bounds for deterministic and randomized 驴-paging algorithms. For deterministic algorithms, we show that an adaptation of LRU is strongly competitive, while for the randomized case we show that by adapting the classical Mark algorithm we get an algorithm with a competitive ratio larger than the lower bound by a multiplicative factor of approximately 1.7.