R-Tree for phase change memory

Jabarov, Elkhan; On, Byung Won; Choi, Gyu Sang; Park, Myong Soon

doi:10.2298/csis160620008j

Cited by 4 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we experimentally validate the construction of the lazy splitting R-tree method and test the query efficiency. To test the performance of the algorithm, we tested our LAZY algorithm (the R-tree using the lazy splitting algorithm), the R-tree using R-tree PM algorithm [16] and the CBS splitting algorithm [14] on the same hardware and software platform.…”

Section: Methodsmentioning

confidence: 99%

“…However, using a perfect hash function as a secondary index structure requires a lot of space, so this scheme is not suitable for large-scale spatial data processing. Jabarov et al [16] proposed an algorithm called R-tree PM algorithm, which doubles the leaf node size and designs a fill factor for the leaf nodes, which is split only when the node data volume reaches the minimum fill factor. Compared with the traditional R-Tree, the R-tree PM algorithm has an average improvement of 23% in processing time, but the R-tree splitting method is too simple and the split R-tree performance is not excellent.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

LAZY R-tree: The R-tree with lazy splitting algorithm

Yang

Bai

et al. 2019

Journal of Information Science

View full text Add to dashboard Cite

The spatial index is a data structure formed according to the position and shape of the spatial object or the relationship between the spatial objects according to certain rules, and the spatial data is managed by an effective spatial data structure. The quality of a spatial index directly affects the performance of spatial queries. The R-tree index structure is a highly efficient spatial index. According to the R-tree query rule, when performing spatial query, most data that is not related to the query condition can be filtered out, and finally, a few leaf nodes can be accessed to query the data satisfying the condition. Its query performance is affected by factors such as non-leaf node overlap and node space utilisation. This article proposes a lazy splitting method to improve the R-tree construction process. The scheme works as follows: (1) When a node overflows, it creates an overflow node for that node and all overflow nodes are saved in a hash table. (2) If the node continues to insert data, the data are added to its overflow node. (3) When an overflow node is saturated, the node and its overflow node are split into two saturated nodes. We use both simulated and actual data to perform experiments. The experimental results show that an R-tree constructed by the lazy algorithm is superior to an R-tree constructed using the original R-tree PM algorithm or the corner-based splitting (CBS) algorithm based on the number of splits created, the node space used and the efficiency of region queries and k-nearest neighbour (kNN) queries.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

LAZY R-tree: The R-tree with lazy splitting algorithm

Yang

Bai

et al. 2019

Journal of Information Science

View full text Add to dashboard Cite

show abstract

“…In [27], a PCM-variant of the R-tree is proposed. R-tree is a well-known index that can handle spatial data.…”

Section: Indexing On Pcmmentioning

confidence: 99%

Adaptive Merging on Phase Change Memory

Macyna¹,

Kukowski²

2022

Preprint

View full text Add to dashboard Cite

Indexing is a well-known database technique used to facilitate data access and speed up query processing. Nevertheless, the construction and modification of indexes are very expensive. In traditional approaches, all records in the database table are equally covered by the index. It is not effective, since some records may be queried very often and some never. To avoid this problem, adaptive merging has been introduced. The key idea is to create index adaptively and incrementally as a side-product of query processing. As a result, the database table is indexed partially depending on the query workload.This paper faces a problem of adaptive merging for phase change memory (PCM). The most important features of this memory type are: limited write endurance and high write latency. As a consequence, adaptive merging should be investigated from the scratch. We solve this problem in two steps. First, we apply several PCM optimization techniques to the traditional adaptive merging approach. We prove that the proposed method (eAM) outperforms a traditional approach by 60%. After that, we invent the framework for adaptive merging (PAM) and a new PCMoptimized index. It further improves the system performance by 20% for databases where search queries interleave with data modifications.

show abstract

Implementation of the Aggregated R-Tree for Phase Change Memory

Jurga

Macyna

2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

R-Tree for phase change memory

Cited by 4 publications

References 8 publications

LAZY R-tree: The R-tree with lazy splitting algorithm

LAZY R-tree: The R-tree with lazy splitting algorithm

Adaptive Merging on Phase Change Memory

Implementation of the Aggregated R-Tree for Phase Change Memory

Contact Info

Product

Resources

About