A parallel search engine with BSP

Abstract

With the technology advance and the growth of Internet, the information that can be found in this net, as well as the number of users that access to look for specific data is bigger. Therefore it is desirable to have a search system that allows to recover information at a reasonable time and in an efficient way. This article describes two strategies based on buckets to improve the efficiency of a classic data structure, the inverted lists, used to index the queries to textual databases. The design of the server that processes the queries, is effected on top of the bulk synchronous model of parallel computing. The main interest is how query performance is performed by the index organization on a cluster of PCs.