Scalable Online Index Construction with Multi-core CPUs

Yamada, H. and Toyama, M.

Inverted index is a core element of current text retrieval systems. They can be dynamically constructed using online indexing approaches in the environment which even a small delay in timeliness cannot be tolerated, and the index must always be queryable and up to date. Recently, efficient online index construction schemes have been proposed, however, previous works have not focused on scalability with the modern commodity hardware resources such as multi-core CPUs. In this paper, we propose a scalable online index construction method that better utilizes multi- core CPUs. Using experiments on 30 GB of web data, we demonstrate the efficiency of our method in practice, showing that it dramatically reduces online index construction time without sacrificing query performance.

Cite as: Yamada, H. and Toyama, M. (2010). Scalable Online Index Construction with Multi-core CPUs. In Proc. 21st Australasian Database Conference (ADC 2010) Brisbane, Australia. CRPIT, 104. Shen H.T. and Bouguettaya, A. Eds., ACS. 29-36

(from crpit.com) (local if available)